1 code implementation • 30 Jan 2024 • Jianbin Jiao, Xina Cheng, WeiJie Chen, Xiaoting Yin, Hao Shi, Kailun Yang
Due to the challenges in data collection, mainstream datasets of 3D human pose estimation are primarily composed of multi-view video data collected in laboratory environments, which contains rich spatial-temporal correlation information besides the image frame content.
1 code implementation • 23 Nov 2023 • Luojun Lin, Zhifeng Shen, Zhishu Sun, Yuanlong Yu, Lei Zhang, WeiJie Chen
The parameters of dynamic networks can be decoupled into a static and a dynamic component, which are designed to learn domain-invariant and domain-specific features, respectively.
1 code implementation • 23 Nov 2023 • Luojun Lin, Zhifeng Shen, Jia-Li Yin, Qipeng Liu, Yuanlong Yu, WeiJie Chen
To this end, we propose a novel MetaFBP framework, in which we devise a universal feature extractor to capture the aesthetic commonality and then optimize to adapt the aesthetic individuality by shifting the decision boundary of the predictor via a meta-learning mechanism.
no code implementations • 25 Oct 2023 • WeiJie Chen, Haoyu Wang, Shicai Yang, Lei Zhang, Wei Wei, Yanning Zhang, Luojun Lin, Di Xie, Yueting Zhuang
Such a one-for-all adaptation paradigm allows us to adapt anything in the world using only one text-to-image generator as well as the corresponding unlabeled target data.
no code implementations • 9 Aug 2023 • WeiJie Chen, Yuhang Wang, Lin Yao
In these methods, only a subset of the input dataset is needed to train neural networks for the estimation of poses and conformations.
no code implementations • 7 Aug 2023 • WeiJie Chen, Xinyan Wang, Yuhang Wang
This has inspired us to combine fragment recognition and structure prediction methods to build a complete structure.
1 code implementation • 1 Jun 2023 • Shubin Huang, Qiong Wu, Yiyi Zhou, WeiJie Chen, Rongsheng Zhang, Xiaoshuai Sun, Rongrong Ji
In addition, we also experiment DVP with the recently popular adapter approach to keep the most parameters of PLMs intact when adapting to VL tasks, helping PLMs achieve a quick shift between single- and multi-modal tasks.
no code implementations • 6 May 2023 • Yafen Ye, Zhihu Xu, Jinhua Zhang, WeiJie Chen, YuanHai Shao
We propose a twin support vector quantile regression (TSVQR) to capture the heterogeneous and asymmetric information in modern data.
2 code implementations • 6 May 2023 • Yufeng Huang, Jiji Tang, Zhuo Chen, Rongsheng Zhang, Xinfeng Zhang, WeiJie Chen, Zeng Zhao, Zhou Zhao, Tangjie Lv, Zhipeng Hu, Wen Zhang
In this paper, we present an end-to-end framework Structure-CLIP, which integrates Scene Graph Knowledge (SGK) to enhance multi-modal structured representations.
1 code implementation • CVPR 2023 • Mingjun Xu, Lingyun Qin, WeiJie Chen, ShiLiang Pu, Lei Zhang
In this work, we present an idea to remove non-causal factors from common features by multi-view adversarial training on source domains, because we observe that such insignificant non-causal factors may still be significant in other latent spaces (views) due to the multi-mode structure of data.
no code implementations • 12 Jan 2023 • Wei Zhao, Binbin Chen, WeiJie Chen, Shicai Yang, Di Xie, ShiLiang Pu, Yueting Zhuang
The domain adaptation part is implemented as a Source-Free Domain Adaptation paradigm, which only uses the pre-trained model and the unlabeled target data to further optimize in a self-supervised training manner.
no code implementations • 12 Jan 2023 • Yilu Guo, Xingyue Shi, WeiJie Chen, Shicai Yang, Di Xie, ShiLiang Pu, Yueting Zhuang
In the test-time training stage, we use the pre-trained model to assign noisy label for the unlabeled target data, and propose a Label-Periodically-Updated DivideMix method for noisy label learning.
no code implementations • CVPR 2023 • WeiJie Chen, Xinyan Wang, Yuhang Wang
This has inspired us to combine fragment recognition and structure prediction methods to build a complete structure.
no code implementations • ICCV 2023 • Weizhen He, WeiJie Chen, Binbin Chen, Shicai Yang, Di Xie, Luojun Lin, Donglian Qi, Yueting Zhuang
In this paper, we delve into this problem and propose an Unsupervised Prompt Tuning framework for text-driven object detection, which is composed of two novel mean teaching mechanisms.
no code implementations • 30 Dec 2022 • Shuyue Guan, Ravi K. Samala, WeiJie Chen
By analyzing the intrinsic properties of these metrics and categorizing the segmentation errors, we are working toward the goal of developing a decision-tree tool for assisting in the selection of segmentation performance metrics.
1 code implementation • 9 Oct 2022 • Rang Meng, Xianfeng Li, WeiJie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Mingli Song, Di Xie, ShiLiang Pu
Under this guidance, a novel Attention Diversification framework is proposed, in which Intra-Model and Inter-Model Attention Diversification Regularization are collaborated to reassign appropriate attention to diverse task-related features.
no code implementations • 5 Jul 2022 • Wenxu Shi, Lei Zhang, WeiJie Chen, ShiLiang Pu
Universal domain adaptive object detection (UniDAOD)is more challenging than domain adaptive object detection (DAOD) since the label space of the source domain may not be the same as that of the target and the scale of objects in the universal scenarios can vary dramatically (i. e, category shift and scale shift).
1 code implementation • LREC 2022 • Jiashu Pu, Ziyi Huang, Yadong Xi, Guandan Chen, WeiJie Chen, Rongsheng Zhang
As neural Text Generation Models (TGM) have become more and more capable of generating text indistinguishable from human-written ones, the misuse of text generation technologies can have serious ramifications.
3 code implementations • CVPR 2022 • Binbin Chen, WeiJie Chen, Shicai Yang, Yunyi Xuan, Jie Song, Di Xie, ShiLiang Pu, Mingli Song, Yueting Zhuang
To remedy this issue, we present a novel label assignment mechanism for self-training framework, namely proposal self-assignment, which injects the proposals from student into teacher and generates accurate pseudo labels to match each proposal in the student model accordingly.
1 code implementation • CVPR 2022 • Rang Meng, WeiJie Chen, Shicai Yang, Jie Song, Luojun Lin, Di Xie, ShiLiang Pu, Xinchao Wang, Mingli Song, Yueting Zhuang
In this paper, we introduce a simple framework, Slimmable Domain Adaptation, to improve cross-domain generalization with a weight-sharing model bank, from which models of different capacities can be sampled to accommodate different accuracy-efficiency trade-offs.
no code implementations • 13 Jun 2022 • Yilu Guo, Shicai Yang, WeiJie Chen, Liang Ma, Di Xie, ShiLiang Pu
Therefore, it is crucial to study how to learn more discriminative representations while avoiding over-fitting.
no code implementations • 13 Jun 2022 • Junchu Huang, WeiJie Chen, Shicai Yang, Di Xie, ShiLiang Pu, Yueting Zhuang
This framework can reduce the impact of noisy labels from CLIP model effectively by combining both techniques.
2 code implementations • 13 Jun 2022 • Meilin Chen, WeiJie Chen, Shicai Yang, Jie Song, Xinchao Wang, Lei Zhang, Yunfeng Yan, Donglian Qi, Yueting Zhuang, Di Xie, ShiLiang Pu
In addition, we conduct anchor adaptation in parallel with localization adaptation, since anchor can be regarded as a learnable parameter.
1 code implementation • 27 May 2022 • Zhishu Sun, Zhifeng Shen, Luojun Lin, Yuanlong Yu, Zhifeng Yang, Shicai Yang, WeiJie Chen
Specifically, we leverage a meta-adjuster to twist the network parameters based on the static model with respect to different data from different domains.
Ranked #23 on Domain Generalization on DomainNet
1 code implementation • ACL 2022 • WeiJie Chen, Yongzhu Chang, Rongsheng Zhang, Jiashu Pu, Guandan Chen, Le Zhang, Yadong Xi, Yijiang Chen, Chang Su
In this paper, we probe simile knowledge from PLMs to solve the SI and SG tasks in the unified framework of simile triple completion for the first time.
1 code implementation • 19 Nov 2021 • Luojun Lin, Han Xie, Zhishu Sun, WeiJie Chen, Wenxi Liu, Yuanlong Yu, Lei Zhang
From this perspective, we introduce a novel paradigm of DG, termed as Semi-Supervised Domain Generalization (SSDG), to explore how the labeled and unlabeled source domains can interact, and establish two settings, including the close-set and open-set SSDG.
no code implementations • 20 May 2021 • Yongfeng Li, Mingming Zhao, WeiJie Chen, Zaiwen Wen
A general theoretical analysis shows that the solutions generated from a sequence of the constrained optimizations converge to the optimal solution of the LP if the error is controlled properly.
no code implementations • 23 Feb 2021 • WeiJie Chen, Luojun Lin, Shicai Yang, Di Xie, ShiLiang Pu, Yueting Zhuang, Wenqi Ren
Usually, the given source domain pre-trained model is expected to optimize with only unlabeled target data, which is termed as source-free unsupervised domain adaptation.
no code implementations • 1 Feb 2021 • WeiJie Chen, Yilu Guo, Shicai Yang, Zhaoyang Li, Zhenxin Ma, Binbin Chen, Long Zhao, Di Xie, ShiLiang Pu, Yueting Zhuang
Therefore, it yields our attention to suppress false positive in each target domain in an unsupervised way.
no code implementations • 10 Dec 2020 • Xianfeng Li, WeiJie Chen, Di Xie, Shicai Yang, Peng Yuan, ShiLiang Pu, Yueting Zhuang
However, it is difficult to evaluate the quality of pseudo labels since no labels are available in target domain.
1 code implementation • 28 Oct 2019 • Yuzhi Zhang, Haidi Wang, WeiJie Chen, Jinzhe Zeng, Linfeng Zhang, Han Wang, Weinan E
Materials 3, 023804] and is capable of generating uniformly accurate deep learning based PES models in a way that minimizes human intervention and the computational cost for data generation and model training.
Computational Physics
1 code implementation • 29 May 2019 • Yuangang Pan, WeiJie Chen, Gang Niu, Ivor W. Tsang, Masashi Sugiyama
Specifically, the properties of our CoarsenRank are summarized as follows: (1) CoarsenRank is designed for mild model misspecification, which assumes there exist the ideal preferences (consistent with model assumption) that locates in a neighborhood of the actual preferences.