no code implementations • 8 May 2024 • He Li, Mang Ye, Ming Zhang, Bo Du
In Re-identification (ReID), recent advancements yield noteworthy progress in both unimodal and cross-modal retrieval tasks.
no code implementations • 2 May 2024 • Tianle Xia, Liang Ding, Guojia Wan, Yibing Zhan, Bo Du, DaCheng Tao
Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs.
1 code implementation • 29 Apr 2024 • Rui Xu, Shu Yang, Yihui Wang, Bo Du, Hao Chen
To help keep pace with the rapid advancements in computer vision, this paper aims to provide a comprehensive review of visual Mamba approaches.
1 code implementation • 27 Apr 2024 • Yuhang Gan, Wenjie Xuan, Hang Chen, Juhua Liu, Bo Du
The C2FG module aims to seamlessly integrate the side prediction from the previous coarse-scale into the current fine-scale prediction in a coarse-to-fine manner, while LF module assumes that the contribution of each stage and each spatial location is independent, thus designing a learnable module to fuse multiple predictions.
no code implementations • 24 Apr 2024 • Xuming An, Dui Wang, Li Shen, Yong Luo, Han Hu, Bo Du, Yonggang Wen, DaCheng Tao
Specifically, FedALC estimates the label correlations in the class embedding learning for different label pairs and utilizes it to improve the model training.
no code implementations • 23 Apr 2024 • Qihuang Zhong, Kang Wang, Ziyang Xu, Juhua Liu, Liang Ding, Bo Du, DaCheng Tao
Chain of Thought prompting strategy has enhanced the performance of Large Language Models (LLMs) across various NLP tasks.
Ranked #1 on Math Word Problem Solving on SVAMP (Accuracy metric)
no code implementations • 6 Apr 2024 • Juncheng Yang, Zuchao Li, Shuai Xie, Wei Yu, Shijun Li, Bo Du
It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the performance of generated prompts.
1 code implementation • 2 Apr 2024 • Quanwei Liu, Yanni Dong, Tao Huang, Lefei Zhang, Bo Du
Therefore, we propose a universal knowledge embedded contrastive learning framework (KnowCL) for supervised, unsupervised, and semisupervised HSI classification, which largely closes the gap between HSI classification models between pocket models and standard vision backbones.
no code implementations • 2 Apr 2024 • Tianhao Zhao, Yongcan Chen, Yu Wu, Tianyang Liu, Bo Du, Peilun Xiao, Shi Qiu, Hongda Yang, Guozhen Li, Yi Yang, Yutian Lin
In the first stage, we train a BEV autoencoder to reconstruct the BEV segmentation maps given corrupted noisy latent representation, which urges the decoder to learn fundamental knowledge of typical BEV patterns.
1 code implementation • 20 Mar 2024 • Di Wang, Jing Zhang, Minqiang Xu, Lin Liu, Dongsheng Wang, Erzhong Gao, Chengxi Han, HaoNan Guo, Bo Du, DaCheng Tao, Liangpei Zhang
However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks.
Ranked #1 on Semantic Segmentation on SpaceNet 1 (using extra training data)
Aerial Scene Classification Building change detection for remote sensing images +13
no code implementations • 18 Mar 2024 • Haoyu Zhao, Yuliang Gu, Zhou Zhao, Bo Du, Yongchao Xu, Rui Yu
Second, to better capture high-frequency components and detailed information, Frequency-Aware Multi-scale Loss (FAM) is proposed by effectively utilizing multi-scale feature space.
1 code implementation • 15 Mar 2024 • Xin Zheng, Dongjin Song, Qingsong Wen, Bo Du, Shirui Pan
This enables the effective evaluation of the well-trained GNNs' ability to capture test node semantics and structural representations, making it an expressive metric for estimating the generalization error in online GNN evaluation.
1 code implementation • 12 Mar 2024 • Tianshuo Peng, Zuchao Li, Lefei Zhang, Hai Zhao, Ping Wang, Bo Du
Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities.
Ranked #25 on Visual Question Answering on MM-Vet
no code implementations • 1 Mar 2024 • Wenjie Xuan, Yufei Xu, Shanshan Zhao, Chaoyue Wang, Juhua Liu, Bo Du, DaCheng Tao
Subsequently, to enhance controllability with inexplicit masks, an advanced Shape-aware ControlNet consisting of a deterioration estimator and a shape-prior modulation block is devised.
no code implementations • 29 Feb 2024 • Boxuan Zhang, Zengmao Wang, Bo Du
The lack of object-level annotations poses a significant challenge for object detection in remote sensing images (RSIs).
no code implementations • 19 Feb 2024 • Qihuang Zhong, Liang Ding, Li Shen, Juhua Liu, Bo Du, DaCheng Tao
Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model.
no code implementations • 19 Feb 2024 • Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
With the development of instruction-tuned large language models (LLMs), improving the safety of LLMs has become more critical.
no code implementations • 5 Feb 2024 • Haoran Li, Jiahua Shi, Huaming Chen, Bo Du, Simon Maksour, Gabrielle Phillips, Mirella Dottori, Jun Shen
Moreover, a novel frequency domain denoising network, named FDNet, is proposed for astrocyte segmentation.
1 code implementation • 31 Jan 2024 • Maoyuan Ye, Jing Zhang, Juhua Liu, Chenyu Liu, BaoCai Yin, Cong Liu, Bo Du, DaCheng Tao
In terms of the AMG mode, Hi-SAM segments text stroke foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing.
Ranked #1 on Hierarchical Text Segmentation on HierText
no code implementations • 21 Jan 2024 • Yunke Wang, Linwei Tao, Bo Du, Yutian Lin, Chang Xu
Adversarial Imitation Learning (AIL) allows the agent to reproduce expert behavior with low-dimensional states and actions.
no code implementations • 19 Jan 2024 • Rui Xu, Yunke Wang, Bo Du
To address these two issues, we propose a novel Masked Autoencoder-enhanced Diffusion Model (MAEDiff) for unsupervised anomaly detection in brain images.
1 code implementation • 17 Jan 2024 • HaoNan Guo, Xin Su, Chen Wu, Bo Du, Liangpei Zhang, Deren Li
Recently, the flourishing large language models(LLM), especially ChatGPT, have shown exceptional performance in language understanding, reasoning, and interaction, attracting users and researchers from multiple fields and domains.
no code implementations • 13 Jan 2024 • Mang Ye, Shuoyi Chen, Chenyue Li, Wei-Shi Zheng, David Crandall, Bo Du
Object Re-Identification (Re-ID) aims to identify and retrieve specific objects from varying viewpoints.
1 code implementation • 12 Jan 2024 • Shuai Wang, Liang Ding, Li Shen, Yong Luo, Bo Du, DaCheng Tao
Advancing automated programming necessitates robust and comprehensive code generation benchmarks, yet current evaluation frameworks largely neglect object-oriented programming (OOP) in favor of functional programming (FP), e. g., HumanEval and MBPP.
1 code implementation • journal 2024 • Sijun Dong, Libo Wang, Bo Du, Xiaoliang Meng
Following this trend, in this study, we introduce ChangeCLIP, a novel framework that leverages robust semantic information from image-text pairs, specifically tailored for Remote Sensing Change Detection (RSCD).
Ranked #4 on Change Detection on CDD Dataset (season-varying)
1 code implementation • 29 Dec 2023 • Xingqiao Li, Jindong Gu, Zhiyong Wang, Yancheng Yuan, Bo Du, Fengxiang He
To address this issue, this paper proposes an eXplainable Multimodal Mortality Predictor (X-MMP) approaching an efficient, explainable AI solution for predicting in-hospital mortality via multimodal ICU data.
1 code implementation • 22 Dec 2023 • Minghui Liao, Guojia Wan, Bo Du
Skeleton Encoder integrates the local information of neurons in a bottom-up manner, with a one-dimensional convolution in neural skeleton's point data; Connectome Encoder uses a graph neural network to capture the topological information of neural circuit; finally, Readout Layer fuses the above two information and outputs classification results.
1 code implementation • 19 Dec 2023 • Weixi Song, Zuchao Li, Lefei Zhang, Hai Zhao, Bo Du
With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue.
no code implementations • 12 Dec 2023 • Yuda Zou, Xin Xiao, Peilin Zhou, Zhichao Sun, Bo Du, Yongchao Xu
Object counting typically uses 2D point annotations.
1 code implementation • 11 Dec 2023 • Anke Tang, Li Shen, Yong Luo, Liang Ding, Han Hu, Bo Du, DaCheng Tao
At the upper level, we focus on learning a shared Concrete mask to identify the subspace, while at the inner level, model merging is performed to maximize the performance of the merged model.
no code implementations • 9 Dec 2023 • Chuang Liu, Yibing Zhan, Xueqi Ma, Liang Ding, Dapeng Tao, Jia Wu, Wenbin Hu, Bo Du
Graph Transformers (GTs) have achieved impressive results on various graph-related tasks.
no code implementations • 8 Dec 2023 • Yang Zhao, Yuxiang Zhang, Yanni Dong, Bo Du
Most change detection models based on vision transformers currently follow a "pretraining then fine-tuning" strategy.
1 code implementation • 4 Dec 2023 • Lu Qi, Lehan Yang, Weidong Guo, Yu Xu, Bo Du, Varun Jampani, Ming-Hsuan Yang
On the other hand, the progressive dichotomy module can efficiently decode the synthesized colormap to high-quality entity-level masks in a depth-first binary search without knowing the cluster numbers.
no code implementations • 21 Nov 2023 • Chuang Liu, Wenhang Yu, Kuang Gao, Xueqi Ma, Yibing Zhan, Jia Wu, Bo Du, Wenbin Hu
Graph pooling has been increasingly recognized as crucial for Graph Neural Networks (GNNs) to facilitate hierarchical graph representation learning.
no code implementations • 17 Nov 2023 • Jiaqi Yang, Bo Du, Liangpei Zhang
Data collected by different modalities can provide a wealth of complementary information, such as hyperspectral image (HSI) to offer rich spectral-spatial properties, synthetic aperture radar (SAR) to provide structural information about the Earth's surface, and light detection and ranging (LiDAR) to cover altitude information about ground elevation.
1 code implementation • 12 Nov 2023 • Wenke Huang, Mang Ye, Zekun Shi, Guancheng Wan, He Li, Bo Du, Qiang Yang
In this survey, we provide a systematic overview of the important and recent developments of research on federated learning.
3 code implementations • ACM Multimedia 2022 • Shuoyi Chen, Mang Ye, Bo Du
Existing methods are usually designed for city cameras, incapable of handing the rotation issue in UAV scenarios.
no code implementations • 20 Oct 2023 • Miaoxi Zhu, Qihuang Zhong, Li Shen, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
The key algorithm in solving ZSAQ is the SAM-SGA optimization, which aims to improve the quantization accuracy and model generalization via optimizing a minimax problem.
1 code implementation • 12 Oct 2023 • Hongling Zheng, Li Shen, Anke Tang, Yong Luo, Han Hu, Bo Du, DaCheng Tao
LFM focuses on the research, modification, and design of FM based on the model interface, so as to better understand the model structure and weights (in a black box environment), and to generalize the model to downstream tasks.
no code implementations • 11 Oct 2023 • Yunke Wang, Minjing Dong, Bo Du, Chang Xu
To tackle these problems, we propose to purify the potential perturbations in imperfect demonstrations and subsequently conduct imitation learning from purified demonstrations.
1 code implementation • 7 Oct 2023 • Anke Tang, Li Shen, Yong Luo, Yibing Zhan, Han Hu, Bo Du, Yixin Chen, DaCheng Tao
We demonstrate that our partial linearization technique enables a more effective fusion of multiple tasks into a single model, outperforming standard adapter tuning and task arithmetic alone.
1 code implementation • 5 Oct 2023 • Kun Li, Yong Luo, Xiantao Cai, Wenbin Hu, Bo Du
In this paper, we propose a zero-shot learning solution for the DRP task in preclinical drug screening.
1 code implementation • 1 Oct 2023 • Hongruixuan Chen, Jian Song, Chen Wu, Bo Du, Naoto Yokoya
Change detection (CD) is a critical task in studying the dynamics of ecosystems and human activities using multi-temporal remote sensing images.
2 code implementations • 28 Sep 2023 • Wenke Huang, Mang Ye, Zekun Shi, Bo Du
Federated learning is an important privacy-preserving multi-party learning paradigm, involving collaborative learning with others and local updating on private data.
1 code implementation • 31 Aug 2023 • Qiang Huang, Jiawei Jiang, Xi Susie Rao, Ce Zhang, Zhichao Han, Zitao Zhang, Xin Wang, Yongjun He, Quanqing Xu, Yang Zhao, Chuang Hu, Shuo Shang, Bo Du
To handle graphs in which features or connectivities are evolving over time, a series of temporal graph neural networks (TGNNs) have been proposed.
no code implementations • 28 Aug 2023 • HaoNan Guo, Xin Su, Chen Wu, Bo Du, Liangpei Zhang
These CD methods, however, still perform far from satisfactorily as we observe that 1) deep encoder layers focus on irrelevant background regions and 2) the models' confidence in the change regions is inconsistent at different decoder stages.
1 code implementation • 15 Aug 2023 • Qiwei Li, Zuchao Li, Xiantao Cai, Bo Du, Hai Zhao
In this paper, we propose GraphLayoutLM, a novel document understanding model that leverages the modeling of layout structure graph to inject document layout knowledge into the model.
no code implementations • 11 Aug 2023 • Rui Xu, Yong Luo, Han Hu, Bo Du, Jialie Shen, Yonggang Wen
Weakly supervised object localization (WSOL) is one of the most popular and challenging tasks in computer vision.
1 code implementation • 28 Jul 2023 • Zhihao LI, Jiancheng Yang, Yongchao Xu, Li Zhang, Wenhui Dong, Bo Du
Extensive experiments on both open-source and in-house datasets consistently demonstrate the effectiveness of the proposed method over some CNN and Transformer-based segmentation methods.
1 code implementation • 27 Jul 2023 • Xiaochen Ma, Bo Du, Zhuohang Jiang, Ahmed Y. Al Hammadi, Jizhe Zhou
To bridge this gap, based on the fact that artifacts are sensitive to image resolution, amplified under multi-scale features, and massive at the manipulation border, we formulate the answer to the former question as building a ViT with high-resolution capacity, multi-scale feature extraction capability, and manipulation edge supervision that could converge with a small amount of data.
1 code implementation • 26 Jul 2023 • Wenjie Xuan, Shanshan Zhao, Yu Yao, Juhua Liu, Tongliang Liu, Yixin Chen, Bo Du, DaCheng Tao
Exploiting the estimated noise transitions, our model, named PNT-Edge, is able to fit the prediction to clean labels.
1 code implementation • 23 Jul 2023 • HaoNan Guo, Bo Du, Chen Wu, Chengxi Han, Liangpei Zhang
To address these issues, we complement the strong temporal modeling ability of metric learning with the prominent fitting ability of segmentation and propose a deep change feature learning (DeepCL) framework for robust and explainable CD.
1 code implementation • 23 Jul 2023 • HaoNan Guo, Bo Du, Chen Wu, Xin Su, Liangpei Zhang
The efficacy of building footprint segmentation from remotely sensed images has been hindered by model transfer effectiveness.
no code implementations • 23 Jul 2023 • HaoNan Guo, Xin Su, Chen Wu, Bo Du, Liangpei Zhang
Compared with many existing methods that train each task individually, the proposed collaborative extraction method can utilize the complementary advantages between buildings and roads by the proposed inter-task and inter-scale feature interactions, and automatically select the optimal reception field for different tasks.
2 code implementations • 20 Jul 2023 • Mang Ye, Xiuwen Fang, Bo Du, Pong C. Yuen, DaCheng Tao
Therefore, a systematic survey on this topic about the research challenges and state-of-the-art is essential.
1 code implementation • 2 Jul 2023 • Yineng Chen, Zuchao Li, Lefei Zhang, Bo Du, Hai Zhao
SGD and Adam are two classical and effective optimizers on which researchers have proposed many variants, such as SGDM and RAdam.
1 code implementation • 22 Jun 2023 • Chuang Liu, Yibing Zhan, Baosheng Yu, Liu Liu, Bo Du, Wenbin Hu, Tongliang Liu
A pooling operation is essential for effective graph-level representation learning, where the node drop pooling has become one mainstream graph pooling technology.
1 code implementation • 19 Jun 2023 • Ting Zhe, YongQian Li, Jing Zhang, Yong Luo, Han Hu, Bo Du, Yonggang Wen, DaCheng Tao
We represent the action information in each hand interaction region as a triplet, resulting in a total of 878 action triplets.
1 code implementation • 19 Jun 2023 • Tianshuo Peng, Zuchao Li, Lefei Zhang, Bo Du, Hai Zhao
To address these deficiencies, we propose the Fuzzy Span Universal Information Extraction (FSUIE) framework.
no code implementations • 8 Jun 2023 • Ziye Chen, Kate Smith-Miles, Bo Du, Guoqi Qian, Mingming Gong
Our method obtains 2D and 3D lane predictions by applying the lane features to the image-view and BEV features, respectively.
1 code implementation • 1 Jun 2023 • Wuxuan Shi, Mang Ye, Bo Du
(2) For the cross-modality gap, we propose a novel Symmetric Uncertainty scheme to remove parts of RGB information harmful to the recovery of HR depth maps.
1 code implementation • 31 May 2023 • Maoyuan Ye, Jing Zhang, Shanshan Zhao, Juhua Liu, Tongliang Liu, Bo Du, DaCheng Tao
In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single decoder with explicit points solo for text detection, recognition, and script identification simultaneously.
Ranked #1 on Text Spotting on Inverse-Text
1 code implementation • 28 May 2023 • Lu Qi, Jason Kuen, Weidong Guo, Jiuxiang Gu, Zhe Lin, Bo Du, Yu Xu, Ming-Hsuan Yang
Despite the progress of image segmentation for accurate visual entity segmentation, completing the diverse requirements of image editing applications for different-level region-of-interest selections remains unsolved.
1 code implementation • 24 May 2023 • Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
Masked language modeling, widely used in discriminative language model (e. g., BERT) pretraining, commonly adopts a random masking strategy.
1 code implementation • 24 May 2023 • Qihuang Zhong, Liang Ding, Juhua Liu, Xuebo Liu, Min Zhang, Bo Du, DaCheng Tao
Token dropping is a recently-proposed strategy to speed up the pretraining of masked language models, such as BERT, by skipping the computation of a subset of the input tokens at several middle layers.
1 code implementation • 23 May 2023 • Anke Tang, Yong Luo, Han Hu, Fengxiang He, Kehua Su, Bo Du, Yixin Chen, DaCheng Tao
This paper studies multiparty learning, aiming to learn a model using the private data of different participants.
no code implementations • 3 May 2023 • Tao Chen, Liang Lv, Di Wang, Jing Zhang, Yue Yang, Zeyang Zhao, Chen Wang, Xiaowei Guo, Hao Chen, Qingye Wang, Yufei Xu, Qiming Zhang, Bo Du, Liangpei Zhang, DaCheng Tao
With the world population rapidly increasing, transforming our agrifood systems to be more productive, efficient, safe, and sustainable is crucial to mitigate potential food shortages.
2 code implementations • NeurIPS 2023 • Di Wang, Jing Zhang, Bo Du, Minqiang Xu, Lin Liu, DaCheng Tao, Liangpei Zhang
In this study, we leverage SAM and existing RS object detection datasets to develop an efficient pipeline for generating a large-scale RS segmentation dataset, dubbed SAMRS.
1 code implementation • 2 May 2023 • Haibin He, Jing Zhang, Mengyang Xu, Juhua Liu, Bo Du, DaCheng Tao
Video text spotting refers to localizing, recognizing, and tracking textual elements such as captions, logos, license plates, signs, and other forms of text within consecutive video frames.
1 code implementation • 23 Apr 2023 • Di Wang, Bo Du, Liangpei Zhang, DaCheng Tao
Recent neural architecture search (NAS) based approaches have made great progress in hyperspectral image (HSI) classification tasks.
2 code implementations • 19 Apr 2023 • Di Wang, Jing Zhang, Bo Du, Liangpei Zhang, DaCheng Tao
Hyperspectral image (HSI) classification is challenging due to spatial variability caused by complex imaging conditions.
no code implementations • 3 Apr 2023 • Rui Xu, Yong Luo, Bo Du
This motivates us to propose a Source-free Unsupervised cross-domain method for Pulmonary nodule detection (SUP).
no code implementations • 24 Mar 2023 • Meiqi Hu, Chen Wu, Bo Du
Hyperspectral change detection plays an essential role of monitoring the dynamic urban development and detecting precise fine object evolution and alteration.
3 code implementations • CVPR 2023 • Zhuo Huang, Miaoxi Zhu, Xiaobo Xia, Li Shen, Jun Yu, Chen Gong, Bo Han, Bo Du, Tongliang Liu
Experimentally, we simulate photon-limited corruptions using CIFAR10/100 and ImageNet30 datasets and show that SharpDRO exhibits a strong generalization ability against severe corruptions and exceeds well-known baseline methods with large performance gains.
no code implementations • 8 Mar 2023 • Xin Yan, Zuchao Li, Lefei Zhang, Bo Du, DaCheng Tao
Our proposed approach, \textbf{CCViT}, leverages k-means clustering to obtain centroids for image modeling without supervised training of tokenizer model.
1 code implementation • 7 Mar 2023 • Rui Xu, Zhi Liu, Yong Luo, Han Hu, Li Shen, Bo Du, Kaiming Kuang, Jiancheng Yang
To address this issue, we propose a slice grouped domain attention (SGDA) module to enhance the generalization capability of the pulmonary nodule detection networks.
1 code implementation • CVPR 2023 • Lixiang Ru, Heliang Zheng, Yibing Zhan, Bo Du
Secondly, to further differentiate the low-confidence regions in CAM, we devised a Class Token Contrast module (CTC) inspired by the fact that class tokens in ViT can capture high-level semantics.
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
1 code implementation • 21 Feb 2023 • Chengxi Han, Chen Wu, Bo Du
Very-high-resolution (VHR) remote sensing (RS) image change detection (CD) has been a challenging task for its very rich spatial information and sample imbalance problem.
Ranked #2 on Change Detection on LEVIR+
1 code implementation • 19 Feb 2023 • Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
Recently, ChatGPT has attracted great attention, as it can generate fluent and high-quality responses to human inquiries.
no code implementations • 18 Feb 2023 • Qihuang Zhong, Liang Ding, Keqin Peng, Juhua Liu, Bo Du, Li Shen, Yibing Zhan, DaCheng Tao
This technical report briefly describes our JDExplore d-team's submission Vega v1 on the General Language Understanding Evaluation (GLUE) leaderboard, where GLUE is a collection of nine natural language understanding tasks, including question answering, linguistic acceptability, sentiment analysis, text similarity, paraphrase detection, and natural language inference.
no code implementations • 16 Feb 2023 • Zhihao Qian, Yutian Lin, Bo Du
In this paper, we propose a Patch-Mixed Cross-Modality framework (PMCM), where two images of the same person from two modalities are split into patches and stitched into a new one for model learning.
1 code implementation • 13 Feb 2023 • Yunke Wang, Bo Du, Chang Xu
The trajectories of an initial agent policy could be closer to those non-optimal expert demonstrations, but within the framework of adversarial imitation learning, agent policy will be optimized to cheat the discriminator and produce trajectories that are similar to those optimal expert demonstrations.
1 code implementation • ICCV 2023 • Ziye Chen, Yu Liu, Mingming Gong, Bo Du, Guoqi Qian, Kate Smith-Miles
While such methods reduce the reliance on specific knowledge, the kernels computed from the key locations fail to capture the lane line's global structure due to its long and thin structure, leading to inaccurate detection of lane lines with complex topologies.
Ranked #1 on Lane Detection on CurveLanes
2 code implementations • CVPR 2023 • Wenke Huang, Mang Ye, Zekun Shi, He Li, Bo Du
The private model presents degenerative performance on other domains (with domain shift).
1 code implementation • 12 Dec 2022 • Haibin He, Xinyuan Chen, Chaoyue Wang, Juhua Liu, Bo Du, DaCheng Tao, Yu Qiao
Specifically, a large stroke-wise dataset is constructed, and a stroke-wise diffusion model is proposed to preserve the structure and the completion of each generated character.
no code implementations • 4 Dec 2022 • Qihuang Zhong, Liang Ding, Yibing Zhan, Yu Qiao, Yonggang Wen, Li Shen, Juhua Liu, Baosheng Yu, Bo Du, Yixin Chen, Xinbo Gao, Chunyan Miao, Xiaoou Tang, DaCheng Tao
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard.
Ranked #1 on Common Sense Reasoning on ReCoRD
1 code implementation • CVPR 2023 • Maoyuan Ye, Jing Zhang, Shanshan Zhao, Juhua Liu, Tongliang Liu, Bo Du, DaCheng Tao
In this paper, we present DeepSolo, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection and recognition simultaneously.
Ranked #1 on Text Spotting on Total-Text (using extra training data)
1 code implementation • 11 Oct 2022 • Qihuang Zhong, Liang Ding, Li Shen, Peng Mi, Juhua Liu, Bo Du, DaCheng Tao
Fine-tuning large pretrained language models on a limited training corpus usually suffers from poor generalization.
2 code implementations • Proceedings of the 30th ACM International Conference on Multimedia 2022 • Wenke Huang, Mang Ye, Bo Du, Xiang Gao
To address these issues, this paper presents a novel framework with two main parts: 1) model agnostic federated learning, it performs public-private communication by unifying the model prediction outputs on the shared public datasets; 2) latent embedding adaptation, it addresses the domain gap with an adversarial learning scheme to discriminate the public and private domains.
1 code implementation • 3 Oct 2022 • Hongruixuan Chen, Naoto Yokoya, Chen Wu, Bo Du
Subsequently, the similarity levels of two structural relationships are calculated from learned graph representations and two difference images are generated based on the similarity levels.
no code implementations • 7 Sep 2022 • Mengya Han, Yibing Zhan, Yong Luo, Bo Du, Han Hu, Yonggang Wen, DaCheng Tao
To address the above issues, we propose a novel metric-based meta-learning framework termed instance-adaptive class representation learning network (ICRL-Net) for few-shot visual recognition.
1 code implementation • 22 Aug 2022 • Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks.
2 code implementations • 8 Aug 2022 • Di Wang, Qiming Zhang, Yufei Xu, Jing Zhang, Bo Du, DaCheng Tao, Liangpei Zhang
Large-scale vision foundation models have made significant progress in visual tasks on natural images, with vision transformers being the primary choice due to their good scalability and representation ability.
Ranked #1 on Aerial Scene Classification on AID (50% as trainset)
1 code implementation • 3 Aug 2022 • Rui Xu, Yong Luo, Bo Du, Kaiming Kuang, Jiancheng Yang
Convolutional neural networks (CNNs) have been demonstrated to be highly effective in the field of pulmonary nodule detection.
1 code implementation • 27 Jul 2022 • Mengya Han, Heliang Zheng, Chaoyue Wang, Yong Luo, Han Hu, Bo Du
Overall, this work is an attempt to explore the internal relevance between generation tasks and perception tasks by prompt designing.
no code implementations • 18 Jul 2022 • Chuang Liu, Xueqi Ma, Yibing Zhan, Liang Ding, Dapeng Tao, Bo Du, Wenbin Hu, Danilo Mandic
However, the LTH-based methods suffer from two major drawbacks: 1) they require exhaustive and iterative training of dense models, resulting in an extremely large training computation cost, and 2) they only trim graph structures and model parameters but ignore the node feature dimension, where significant redundancy exists.
no code implementations • 14 Jul 2022 • Xingping Dong, Shengcai Liao, Bo Du, Ling Shao
Most existing few-shot learning (FSL) methods require a large amount of labeled data in meta-training, which is a major limit.
1 code implementation • 10 Jul 2022 • Maoyuan Ye, Jing Zhang, Shanshan Zhao, Juhua Liu, Bo Du, DaCheng Tao
However, these methods built upon detection transformer framework might achieve sub-optimal training efficiency and performance due to coarse positional query modeling. In addition, the point label form exploited in previous works implies the reading order of humans, which impedes the detection robustness from our observation.
Ranked #3 on Scene Text Detection on SCUT-CTW1500
1 code implementation • 7 Jul 2022 • Kaiming Kuang, Li Zhang, Jingyu Li, Hongwei Li, Jiajun Chen, Bo Du, Jiancheng Yang
The automatic reconstruction of pulmonary segments by ImPulSe is accurate in metrics and visually appealing.
1 code implementation • 15 Jun 2022 • Xiaowen Wei, Xiuwen Gong, Yibing Zhan, Bo Du, Yong Luo, Wenbin Hu
Experimental results on real-world networks demonstrate that CLNode is a general framework that can be combined with various GNNs to improve their accuracy and robustness.
1 code implementation • 30 May 2022 • Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, DaCheng Tao
To verify our hypothesis, we first empirically study the functionalities of the encoder and decoder in seq2seq pretrained language models, and find that the encoder takes an important but under-exploitation role than the decoder regarding the downstream performance and neuron activation.
1 code implementation • 30 May 2022 • Chaojian Yu, Bo Han, Mingming Gong, Li Shen, Shiming Ge, Bo Du, Tongliang Liu
Based on these observations, we propose a robust perturbation strategy to constrain the extent of weight perturbation.
no code implementations • 23 May 2022 • Meiqi Hu, Chen Wu, Bo Du
Hyperspectral anomalous change detection has been a challenging task for its emphasis on the dynamics of small and rare objects against the prevalent changes.
1 code implementation • 15 Apr 2022 • Chuang Liu, Yibing Zhan, Jia Wu, Chang Li, Bo Du, Wenbin Hu, Tongliang Liu, DaCheng Tao
Graph neural networks have emerged as a leading architecture for many graph-level tasks, such as graph classification and graph generation.
2 code implementations • 6 Apr 2022 • Di Wang, Jing Zhang, Bo Du, Gui-Song Xia, DaCheng Tao
To this end, we train different networks from scratch with the help of the largest RS scene recognition dataset up to now -- MillionAID, to obtain a series of RS pretrained backbones, including both convolutional neural networks (CNN) and vision transformers such as Swin and ViTAE, which have shown promising performance on computer vision tasks.
Ranked #1 on Aerial Scene Classification on UCM (80% as trainset)
Aerial Scene Classification Building change detection for remote sensing images +5
1 code implementation • 1 Apr 2022 • Jia Liu, Wenjie Xuan, Yuhang Gan, Juhua Liu, Bo Du
In this paper, we propose an end-to-end Supervised Domain Adaptation framework for cross-domain Change Detection, namely SDACD, to effectively alleviate the domain shift between bi-temporal images for better change predictions.
Change Detection Change detection for remote sensing images +1
1 code implementation • CVPR 2022 • Lixiang Ru, Yibing Zhan, Baosheng Yu, Bo Du
Motivated by the inherent consistency between the self-attention in Transformers and the semantic affinity, we propose an Affinity from Attention (AFA) module to learn semantic affinity from the multi-head self-attention (MHSA) in Transformers.
Ranked #28 on Weakly-Supervised Semantic Segmentation on COCO 2014 val
Weakly supervised Semantic Segmentation Weakly-Supervised Semantic Segmentation
no code implementations • 3 Mar 2022 • Yunke Wang, Bo Du, Wenyuan Wang, Chang Xu
To satisfy the sequential input of Transformer, the tail of ViT first splits each image into a sequence of visual tokens with a fixed length.
1 code implementation • 10 Feb 2022 • Lixiang Ru, Bo Du, Yibing Zhan, Chen Wu
In the visual words learning module, we counter the first problem by enforcing the classification network to learn fine-grained visual word labels so that more object extents could be discovered.
1 code implementation • 18 Jan 2022 • Chao Chen, Yibing Zhan, Baosheng Yu, Liu Liu, Yong Luo, Bo Du
To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation.
1 code implementation • 16 Jan 2022 • Chen Wu, Bo Du, Liangpei Zhang
Deep learning for change detection is one of the current hot topics in the field of remote sensing.
1 code implementation • 13 Jan 2022 • Qihuang Zhong, Liang Ding, Juhua Liu, Bo Du, Hua Jin, DaCheng Tao
To this end, we propose a knowledge graph augmented network KGAN, which aims to effectively incorporate external knowledge with explicitly syntactic and contextual information.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
1 code implementation • CVPR 2022 • Wenke Huang, Mang Ye, Bo Du
Federated learning has emerged as an important distributed learning paradigm, which normally involves collaborative updating with others and local updating on private data.
1 code implementation • CVPR 2022 • Ziyi Liu, Zengmao Wang, Bo Du
In this paper, we propose a deep protein subcellular localization method with multi-marginal contrastive learning to perceive the same PSLs in different tissue images and different PSLs within the same tissue image.
1 code implementation • AAAI 2022 2021 • Yue He, Chen Chen, Jing Zhang, Juhua Liu, Fengxiang He, Chaoyue Wang, Bo Du
Technically, given the character segmentation maps predicted by a VR model, we construct a subgraph for each instance, where nodes represent the pixels in it and edges are added between nodes based on their spatial similarity.
Ranked #10 on Scene Text Recognition on ICDAR2015 (using extra training data)
1 code implementation • 19 Dec 2021 • Liang Zhang, Qiang Wu, Jun Shen, Linyuan Lü, Bo Du, Jianqing Wu
Many studies confirmed that a proper traffic state representation is more important than complex algorithms for the classical traffic signal control (TSC) problem.
1 code implementation • 15 Dec 2021 • Yonghao Xu, Fengxiang He, Bo Du, DaCheng Tao, Liangpei Zhang
In SE-GAN, a teacher network and a student network constitute a self-ensembling model for generating semantic segmentation maps, which together with a discriminator, forms a GAN.
no code implementations • 8 Dec 2021 • Meiqi Hu, Chen Wu, Bo Du, Liangpei Zhang
In this study, we proposed an unsupervised Binary Change Guided hyperspectral multiclass change detection Network (BCG-Net) for HMCD, which aims at boosting the multiclass change detection result and unmixing result with the mature binary change detection approaches.
1 code implementation • 4 Dec 2021 • Qiang Wu, Liang Zhang, Jun Shen, Linyuan Lü, Bo Du, Jianqing Wu
Since conventional approaches could not adapt to dynamic traffic conditions, reinforcement learning (RL) has attracted more attention to help solve the traffic signal control (TSC) problem.
no code implementations • 4 Nov 2021 • Xiaoyang Guo, Tianhao Zhao, Yutian Lin, Bo Du
In this way, the model could access more variant data samples of an instance and keep predicting invariant discriminative representations for them.
1 code implementation • 26 Oct 2021 • Juhua Liu, Qihuang Zhong, Liang Ding, Hua Jin, Bo Du, DaCheng Tao
In practice, we formulate the model pretrained on the sampled instances into a knowledge guidance model and a learner model, respectively.
Aspect-Based Sentiment Analysis Aspect-Based Sentiment Analysis (ABSA) +2
no code implementations • 15 Oct 2021 • Ziyi Liu, Minghui Liao, Fulin Luo, Bo Du
This method constructs the graph by the similarity relationship between cells and adopts GCN to analyze the neighbor embedding information of samples, which makes the similar cell closer to each other on the 2D scatter plot.
no code implementations • 18 Sep 2021 • Hongruixuan Chen, Chen Wu, Yonghao Xu, Bo Du
To this end, a semantic-edge domain adaptation architecture is proposed, which uses an independent edge stream to process edge information, thereby generating high-quality semantic boundaries over the target domain.
Ranked #34 on Synthetic-to-Real Translation on GTAV-to-Cityscapes Labels (using extra training data)
1 code implementation • 16 Sep 2021 • Xue Jiang, Jianhui Zhao, Bo Du, Zhiyong Yuan
In detail, the network's performance depends on the choice of transformations and the amount of unlabeled data used in the training process of self-supervised learning.
1 code implementation • 18 Aug 2021 • Hongruixuan Chen, Chen Wu, Bo Du
With the goal of designing a quite deep architecture to obtain more precise CD results while simultaneously decreasing parameter numbers to improve efficiency, in this work, we present a very deep and efficient CD network, entitled EffCDNet.
1 code implementation • 18 Aug 2021 • Jiajun Huang, Xueyu Wang, Bo Du, Pei Du, Chang Xu
It includes 10, 000 facial animation videos in ten different actions, which can spoof the recent liveness detectors.
2 code implementations • 16 Aug 2021 • Tianyang Liu, Yutian Lin, Bo Du
State-of-the-art unsupervised re-ID methods usually follow a clustering-based strategy, which generates pseudo labels by clustering and maintains a memory to store instance features and represent the centroid of the clusters for contrastive learning.
1 code implementation • 3 Aug 2021 • Bo Du, Jian Ye, Jing Zhang, Juhua Liu, DaCheng Tao
Existing methods for arbitrary-shaped text detection in natural scenes face two critical issues, i. e., 1) fracture detections at the gaps in a text instance; and 2) inaccurate detections of arbitrary-shaped text instances with diverse background context.
Ranked #5 on Scene Text Detection on SCUT-CTW1500
2 code implementations • 26 Jun 2021 • Di Wang, Bo Du, Liangpei Zhang
To tackle these problems, in this paper, different from previous approaches, we perform the superpixel generation on intermediate features during network training to adaptively produce homogeneous regions, obtain graph structures, and further generate spatial descriptors, which are served as graph nodes.
1 code implementation • 8 Apr 2021 • Yonghao Xu, Bo Du, Liangpei Zhang
Since the collection of pixel-level annotations for HSI is laborious and time-consuming, developing algorithms that can yield good performance in the small sample size situation is of great significance.
no code implementations • 2 Mar 2021 • Chen Wu, Sihan Zhu, Jiaqi Yang, Meiqi Hu, Bo Du, Liangpei Zhang, Lefei Zhang, Chengxi Han, Meng Lan
Considering that public transportation was mostly reduced or even forbidden, our results indicate that city lockdown policies are effective at limiting human transmission within cities.
no code implementations • 1 Mar 2021 • Ziqing Lu, Chang Xu, Bo Du, Takashi Ishida, Lefei Zhang, Masashi Sugiyama
In neural networks, developing regularization algorithms to settle overfitting is one of the major study areas.
no code implementations • 24 Feb 2021 • Shao-Chun Zhang, Hao-Bin Lin, Yang Dong, Bo Du, Xue-Dong Gao, Cui Yu, Zhi-Hong Feng, Xiang-Dong Chen, Guang-Can Guo, Fang-Wen Sun
Nitrogen-vacancy quantum defects in diamond offer a promising platform for magnetometry because of their remarkable optical and spin properties.
Applied Physics Quantum Physics
no code implementations • ICCV 2021 • Lin Zhang, Yong Luo, Yan Bai, Bo Du, Ling-Yu Duan
Federated Learning (FL) aims to establish a shared model across decentralized clients under the privacy-preserving constraint.
no code implementations • ICCV 2021 • Ziye Chen, Yibing Zhan, Baosheng Yu, Mingming Gong, Bo Du
Despite their efficiency, current graph-based predictors treat all operations equally, resulting in biased topological knowledge of cell architectures.
1 code implementation • ICCV 2021 • Mang Ye, Weijian Ruan, Bo Du, Mike Zheng Shou
This paper introduces a powerful channel augmented joint learning strategy for the visible-infrared recognition problem.
no code implementations • 11 Nov 2020 • Xinjian Huang, Weiwei Liu, Bo Du, DaCheng Tao
In this paper, we employ the leverage scores to characterize the importance of each element and significantly relax assumptions to: (1) not any other structure assumptions are imposed on the underlying low-rank matrix; (2) elements being observed are appropriately dependent on their importance via the leverage score.
1 code implementation • 27 Oct 2020 • Meiqi Hu, Chen Wu, Liangpei Zhang, Bo Du
In the ACDA model, two systematic auto-encoder (AE) networks are deployed to construct two predictors from two directions.
1 code implementation • 12 Oct 2020 • Kunping Yang, Gui-Song Xia, Zicheng Liu, Bo Du, Wen Yang, Marcello Pelillo, Liangpei Zhang
Given two multi-temporal aerial images, semantic change detection aims to locate the land-cover variations and identify their change types with pixel-wise boundaries.
1 code implementation • CVPR 2020 • Jingyuan Li, Ning Wang, Lefei Zhang, Bo Du, DaCheng Tao
To capture information from distant places in the feature map for RFR, we further develop KCA and incorporate it in RFR.
1 code implementation • 8 Jul 2020 • Chunwei Tian, Yong Xu, WangMeng Zuo, Bo Du, Chia-Wen Lin, David Zhang
The enhancement block gathers and fuses the global and local features to provide complementary information for the latter network.
no code implementations • ACL 2020 • YUREN MAO, Shuang Yun, Weiwei Liu, Bo Du
Multi-task Learning methods have achieved great progress in text classification.
no code implementations • 26 Jun 2020 • Chen Wu, Yinong Guo, HaoNan Guo, Jingwen Yuan, Lixiang Ru, Hongruixuan Chen, Bo Du, Liangpei Zhang
The significant reduction and recovery of traffic density indicates that the lockdown policy in Wuhan show effectiveness in controlling human transmission inside the city, and the city returned to normal after lockdown lift.
no code implementations • 16 Jun 2020 • Hongruixuan Chen, Chen Wu, Bo Du, Liangpei Zhang
By optimizing the network parameters and kernel coefficients with the source labeled data and target unlabeled data, DSDANet can learn transferrable feature representation that can bridge the discrepancy between two domains.
1 code implementation • 3 Jun 2020 • Qikui Zhu, Bo Du, Pingkun Yan
Furthermore, the adjacency matrix is usually pre-defined and stationary, which makes the data augmentation strategies cannot be employed on the constructed graph structures data to augment the amount of training data.
1 code implementation • 3 Jun 2020 • Lixiang Ru, Bo Du, Chen Wu
In this work, we proposed a CorrFusion module that fuses the highly correlated components in bi-temporal feature embeddings.
6 code implementations • 17 May 2020 • Jian Ye, Zhe Chen, Juhua Liu, Bo Du
More specifically, we propose to perceive texts from three levels of feature representations, i. e., character-, word- and global-level, and then introduce a novel text representation fusion technique to help achieve robust arbitrary text detection.
Ranked #1 on Scene Text Detection on ICDAR 2015
no code implementations • 13 Apr 2020 • Hongruixuan Chen, Chen Wu, Bo Du, Liangepei Zhang
In this paper, we propose a novel deep siamese domain adaptation convolutional neural network (DSDANet) architecture for cross-domain change detection.
no code implementations • 5 Dec 2019 • Qikui Zhu, Bo Du, Pingkun Yan
Furthermore, instead of using image based similarity for label fusion, which can be distracted by the large background areas, we propose a novel strategy to compute the label similarity based weights for label fusion.
1 code implementation • 12 Nov 2019 • Qikui Zhu, Bo Du, Pingkun Yan
To address the above weaknesses, in this paper, we propose a new method of multi-hop convolutional network on weighted graphs.
no code implementations • 24 Oct 2019 • Xi Fang, Bo Du, Sheng Xu, Bradford J. Wood, Pingkun Yan
Automatic medical image segmentation, an essential component of medical image analysis, plays an importantrole in computer-aided diagnosis.
3 code implementations • 27 Jun 2019 • Hongruixuan Chen, Chen Wu, Bo Du, Liangpei Zhang
Based on the unit two novel deep siamese convolutional neural networks, called as deep siamese multi-scale convolutional network (DSMS-CN) and deep siamese multi-scale fully convolutional network (DSMS-FCN), are designed for unsupervised and supervised change detection, respectively.
1 code implementation • 14 May 2019 • Sheng Wan, Chen Gong, Ping Zhong, Bo Du, Lefei Zhang, Jian Yang
To alleviate this shortcoming, we consider employing the recently proposed Graph Convolutional Network (GCN) for hyperspectral image classification, as it can conduct the convolution on arbitrarily structured non-Euclidean data and is applicable to the irregular image regions represented by graph topological information.
no code implementations • 14 Apr 2019 • Bo Du, Zengmao Wang, Lefei Zhang, Liangpei Zhang, Wei Liu, Jialie Shen, DaCheng Tao
Then can we find a way to fuse the two active sampling criteria without any assumption on data?
no code implementations • 14 Apr 2019 • Bo Du, Zengmao Wang, Lefei Zhang, Liangpei Zhang, DaCheng Tao
Meanwhile, it is also hard to build a good model without diagnosing discriminative labels.
no code implementations • 8 Apr 2019 • Lefei Zhang, Qian Zhang, Bo Du, Xin Huang, Yuan Yan Tang, DaCheng Tao
In a feature representation point of view, a nature approach to handle this situation is to concatenate the spectral and spatial features into a single but high dimensional vector and then apply a certain dimension reduction technique directly on that concatenated vector before feed it into the subsequent classifier.
no code implementations • CVPR 2019 • Sheng Li, Fengxiang He, Bo Du, Lefei Zhang, Yonghao Xu, DaCheng Tao
Recently, deep learning based video super-resolution (SR) methods have achieved promising performance.
1 code implementation • 21 Feb 2019 • Qikui Zhu, Bo Du, Pingkun Yan
To make the network more sensitive to the boundaries during segmentation, a boundary-weighted segmentation loss (BWL) is proposed.
1 code implementation • 3 Dec 2018 • Bo Du, Lixiang Ru, Chen Wu, Liangpei Zhang
In recent years, deep network has shown its brilliant performance in many fields including feature extraction and projection.
no code implementations • 23 Nov 2018 • Meng Lan, YiPeng Zhang, Lefei Zhang, Bo Du
In this work, we study the performance of the region-based CNN for the electrical equipment defect detection by using the UAV images.
no code implementations • 19 Aug 2018 • Pan Xiao, Bo Du, Jia Wu, Lefei Zhang, Ruimin Hu, Xuelong. Li
Many classic methods solve the domain adaptation problem by establishing a common latent space, which may cause the loss of many important properties across both domains.
3 code implementations • 30 Jul 2018 • Liangchen Song, Cheng Wang, Lefei Zhang, Bo Du, Qian Zhang, Chang Huang, Xinggang Wang
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation.
Ranked #15 on Unsupervised Domain Adaptation on Market to Duke
1 code implementation • ISPRS Journal of Photogrammetry and Remote Sensing 2018 • Yonghao Xu, Bo Du, Fan Zhang, Liangpei Zhang
Due to the remarkable achievements obtained by deep learning methods in the fields of computer vision, an increasing number of researches have been made to apply these powerful tools into hyperspectral image (HSI) classification.
no code implementations • 25 Apr 2018 • Bo Du, Shihan Cai, Chen Wu, Liangpei Zhang, DaCheng Tao
Object tracking is a hot topic in computer vision.
no code implementations • 22 Mar 2017 • Qikui Zhu, Bo Du, Baris Turkbey, Peter L . Choyke, Pingkun Yan
Prostate segmentation from Magnetic Resonance (MR) images plays an important role in image guided interven- tion.
no code implementations • 26 Feb 2017 • Fan Zhang, Bo Du, Liangpei Zhang
For the second target, a novel CNN-based universal framework is proposed to process the VHR satellite images and generate the land-use, urban density, and population distribution maps.