no code implementations • 7 Apr 2024 • Xin Pang, Zhucong Li, Jiaxiang Chen, Yuan Cheng, Yinghui Xu, Yuan Qi
We introduce AI2Apps, a Visual Integrated Development Environment (Visual IDE) with full-cycle capabilities that accelerates developers to build deployable LLM-based AI agent Applications.
1 code implementation • 21 Mar 2024 • Shenhao Zhu, Junming Leo Chen, Zuozhuo Dai, Yinghui Xu, Xun Cao, Yao Yao, Hao Zhu, Siyu Zhu
In this study, we introduce a methodology for human image animation by leveraging a 3D human parametric model within a latent diffusion framework to enhance shape alignment and motion guidance in curernt human generative techniques.
no code implementations • 9 Dec 2023 • Zhenting Qi, Xiaoyu Tan, Shaojie Shi, Chao Qu, Yinghui Xu, Yuan Qi
Instruction fine-tuning has conventionally been employed to adapt Large Language Models (LLMs) to a variety of tasks.
2 code implementations • 12 Nov 2023 • Qiang Zhou, Zhibin Wang, Wei Chu, Yinghui Xu, Hao Li, Yuan Qi
Our experiments demonstrate that preserving the positional information of visual embeddings through the pool-adapter is particularly beneficial for tasks like visual grounding.
Ranked #66 on Visual Question Answering on MM-Vet
2 code implementations • 22 Jun 2023 • Lei Chen, Xiaohui Zhong, Feng Zhang, Yuan Cheng, Yinghui Xu, Yuan Qi, Hao Li
Over the past few years, due to the rapid development of machine learning (ML) models for weather forecasting, state-of-the-art ML models have shown superior performance compared to the European Centre for Medium-Range Weather Forecasts (ECMWF)'s high-resolution forecast (HRES) in 10-day forecasts at a spatial resolution of 0. 25 degree.
no code implementations • CVPR 2021 • Liuyihan Song, Kang Zhao, Pan Pan, Yu Liu, Yingya Zhang, Yinghui Xu, Rong Jin
Different from all of them, we regard large and small gradients selection as the exploitation and exploration of gradient information, respectively.
no code implementations • 16 Jun 2021 • Shuyi Qu, Zhenxing Niu, Kaizhu Huang, Jianke Zhu, Matan Protter, Gadi Zimerman, Yinghui Xu
Recent deep generative models have achieved promising performance in image inpainting.
no code implementations • 19 May 2021 • Yiming Chen, Kun Yuan, Yingya Zhang, Pan Pan, Yinghui Xu, Wotao Yin
Communication overhead hinders the scalability of large-scale distributed training.
1 code implementation • ICCV 2021 • Kun Yuan, Yiming Chen, Xinmeng Huang, Yingya Zhang, Pan Pan, Yinghui Xu, Wotao Yin
Experimental results on a variety of computer vision tasks and models demonstrate that DecentLaM promises both efficient and high-quality training.
no code implementations • CVPR 2021 • Li Hu, Peng Zhang, Bang Zhang, Pan Pan, Yinghui Xu, Rong Jin
To address this limitation, we propose to Learn position and target Consistency framework for Memory-based video object segmentation, termed as LCM.
no code implementations • CVPR 2021 • Qiang Wang, Yun Zheng, Pan Pan, Yinghui Xu
Recent works have shown that convolutional networks have substantially improved the performance of multiple object tracking by simultaneously learning detection and appearance features.
1 code implementation • CVPR 2021 • Chi Zhang, Nan Song, Guosheng Lin, Yun Zheng, Pan Pan, Yinghui Xu
First, we adopt a simple but effective decoupled learning strategy of representations and classifiers that only the classifiers are updated in each incremental session, which avoids knowledge forgetting in the representations.
Ranked #7 on Few-Shot Class-Incremental Learning on CIFAR-100
1 code implementation • CVPR 2021 • Lianghua Huang, Yu Liu, Bin Wang, Pan Pan, Yinghui Xu, Rong Jin
A key challenge in self-supervised video representation learning is how to effectively capture motion information besides context bias.
2 code implementations • ICCV 2021 • Mo Zhou, Le Wang, Zhenxing Niu, Qilin Zhang, Yinghui Xu, Nanning Zheng, Gang Hua
In this paper, we formulate a new adversarial attack against deep ranking systems, i. e., the Order Attack, which covertly alters the relative order among a selected set of candidates according to an attacker-specified permutation, with limited interference to other unrelated candidates.
no code implementations • 9 Feb 2021 • Yu Liu, Lianghua Huang, Pan Pan, Bin Wang, Yinghui Xu, Rong Jin
However, scaling up the classification task from thousands of semantic labels to millions of instance labels brings specific challenges including 1) the large-scale softmax computation; 2) the slow convergence due to the infrequent visiting of instance samples; and 3) the massive number of negative classes that can be noisy.
no code implementations • 9 Feb 2021 • Kang Zhao, Pan Pan, Yun Zheng, Yanhao Zhang, Changxu Wang, Yingya Zhang, Yinghui Xu, Rong Jin
For a deployed visual search system with several billions of online images in total, building a billion-scale offline graph in hours is essential, which is almost unachievable by most existing methods.
no code implementations • 9 Feb 2021 • Kang Zhao, Sida Huang, Pan Pan, Yinghan Li, Yingya Zhang, Zhenyu Gu, Yinghui Xu
Researches have demonstrated that low bit-width (e. g., INT8) quantization can be employed to accelerate the inference process.
no code implementations • 9 Feb 2021 • Yanhao Zhang, Qiang Wang, Pan Pan, Yun Zheng, Cheng Da, Siyang Sun, Yinghui Xu
Nowadays, live-stream and short video shopping in E-commerce have grown exponentially.
no code implementations • 9 Feb 2021 • Yanhao Zhang, Pan Pan, Yun Zheng, Kang Zhao, Jianmin Wu, Yinghui Xu, Rong Jin
Benefiting from exploration of user click data, our networks are more effective to encode richer supervision and better distinguish real-shot images in terms of category and feature.
no code implementations • 9 Feb 2021 • Xiangzeng Zhou, Pan Pan, Yun Zheng, Yinghui Xu, Rong Jin
In this paper, we present a novel side information based large scale visual recognition co-training~(SICoT) system to deal with the long tail problem by leveraging the image related side information.
no code implementations • 9 Feb 2021 • Liuyihan Song, Pan Pan, Kang Zhao, Hao Yang, Yiming Chen, Yingya Zhang, Yinghui Xu, Rong Jin
In the last decades, extreme classification has become an essential topic for deep learning.
1 code implementation • 10 Dec 2020 • Bowen Cai, Huan Fu, Rongfei Jia, Binqiang Zhao, Hua Li, Yinghui Xu
Adapting semantic segmentation models to new domains is an important but challenging problem.
no code implementations • ECCV 2020 • Lele Cheng, Xiangzeng Zhou, Liming Zhao, Dangwei Li, Hong Shang, Yun Zheng, Pan Pan, Yinghui Xu
In many real-world datasets, like WebVision, the performance of DNN based classifier is often limited by the noisy labeled data.
no code implementations • 19 Aug 2020 • Lu Duan, Haoyuan Hu, Zili Wu, Guozheng Li, Xinhang Zhang, Yu Gong, Yinghui Xu
In this paper, rather than designing heuristics, we propose an end-to-end learning and optimization framework named Balanced Task-orientated Graph Clustering Network (BTOGCN) to solve the BOBP by reducing it to balanced graph clustering optimization problem.
no code implementations • 23 Jun 2019 • Jian-Ya Ding, Chao Zhang, Lei Shen, Shengyin Li, Bing Wang, Yinghui Xu, Le Song
In many applications, a similar MIP model is solved on a regular basis, maintaining remarkable similarities in model structures and solution appearances but differing in formulation coefficients.
no code implementations • 7 Mar 2019 • Yujie Chen, Yu Qian, Yichen Yao, Zili Wu, Rongqi Li, Yinzhi Zhou, Haoyuan Hu, Yinghui Xu
In this paper, we study a courier dispatching problem (CDP) raised from an online pickup-service platform of Alibaba.
no code implementations • 17 Apr 2018 • Lu Duan, Haoyuan Hu, Yu Qian, Yu Gong, Xiaodong Zhang, Yinghui Xu, Jiangwen Wei
A 3D flexible bin packing problem (3D-FBPP) arises from the process of warehouse packing in e-commerce.
1 code implementation • 2 Mar 2018 • Yujing Hu, Qing Da, An-Xiang Zeng, Yang Yu, Yinghui Xu
For better utilizing the correlation between different ranking steps, in this paper, we propose to use reinforcement learning (RL) to learn an optimal ranking policy which maximizes the expected accumulative rewards in a search session.
no code implementations • 20 Aug 2017 • Haoyuan Hu, Xiaodong Zhang, Xiaowei Yan, Longfei Wang, Yinghui Xu
The objective is to find a way to place these items that can minimize the surface area of the bin.
3 code implementations • 30 May 2017 • Jun Wang, Lantao Yu, Wei-Nan Zhang, Yu Gong, Yinghui Xu, Benyou Wang, Peng Zhang, Dell Zhang
This paper provides a unified account of two schools of thinking in information retrieval modelling: the generative retrieval focusing on predicting relevant documents given a query, and the discriminative retrieval focusing on predicting relevancy given a query-document pair.