no code implementations • 5 Mar 2024 • Bin Zhang, Yuxiao Ye, Guoqing Du, Xiaoru Hu, Zhishuai Li, Sun Yang, Chi Harold Liu, Rui Zhao, Ziyue Li, Hangyu Mao
Then we formulate five evaluation tasks to comprehensively assess the performance of diverse methods across various LLMs throughout the Text-to-SQL process. Our study highlights the performance disparities among LLMs and proposes optimal in-context learning solutions tailored to each task.
no code implementations • 17 Jan 2024 • Yinuo Zhao, Kun Wu, Tianjiao Yi, Zhiyuan Xu, Xiaozhu Ju, Zhengping Che, Qinru Qiu, Chi Harold Liu, Jian Tang
Visuomotor policies, which learn control mechanisms directly from high-dimensional visual observations, confront challenges in adapting to new environments with intricate visual variations.
no code implementations • 29 Dec 2023 • Hao Wang, Bo Tang, Chi Harold Liu, Shangqin Mao, Jiahong Zhou, Zipeng Dai, Yaqi Sun, Qianlong Xie, Xingxing Wang, Dong Wang
Online display advertising platforms service numerous advertisers by providing real-time bidding (RTB) for the scale of billions of ad requests every day.
1 code implementation • ICCV 2023 • Zekang Zhang, Guangyu Gao, Jianbo Jiao, Chi Harold Liu, Yunchao Wei
However, most state-of-the-art methods use the freeze strategy for stability, which compromises the model's plasticity. In contrast, releasing parameter training for plasticity could lead to the best performance for all categories, but this requires discriminative feature representation. Therefore, we prioritize the model's plasticity and propose the Contrast inter- and intra-class representations for Incremental Segmentation (CoinSeg), which pursues discriminative representations for flexible parameter tuning.
1 code implementation • 27 Feb 2023 • Mixue Xie, Shuang Li, Rui Zhang, Chi Harold Liu
Active domain adaptation (DA) aims to maximally boost the model adaptation on a new target domain by actively selecting limited target data to annotate, whereas traditional active learning methods may be less effective since they do not consider the domain shift issue.
no code implementations • 17 Jan 2023 • Xiangwei Wang, Rui Han, Chi Harold Liu
In addition, in order to further reduce the computational overhead for unlabeled samples, EdgeHML leverages a progressive learning method.
1 code implementation • ICCV 2023 • Wenxuan Ma, Shuang Li, Jinming Zhang, Chi Harold Liu, Jingxuan Kang, Yulin Wang, Gao Huang
To address this issue, this paper presents a novel approach that seeks to leverage linguistic knowledge for data-efficient visual learning.
no code implementations • CVPR 2023 • Zhenjie Yu, Shuang Li, Yirui Shen, Chi Harold Liu, Shuigen Wang
Explicit visible videos can provide sufficient visual information and facilitate vision applications.
no code implementations • 4 Dec 2022 • Yaxin Luopan, Rui Han, Qinglong Zhang, Chi Harold Liu, Guoren Wang
Upon training for a new task, the gradient integrator ensures the prevention of catastrophic forgetting and mitigation of negative knowledge transfer by effectively combining signature tasks identified from the past local tasks and other clients' current tasks through the global model.
1 code implementation • 22 Nov 2022 • Mingjia Li, Binhui Xie, Shuang Li, Chi Harold Liu, Xinjing Cheng
However, previous methods often reckon on additional reference images of the same scenes taken from normal conditions, which are quite tough to collect in reality.
Ranked #8 on Domain Adaptation on Cityscapes to ACDC
1 code implementation • 2 Aug 2022 • Wenxuan Ma, Jinming Zhang, Shuang Li, Chi Harold Liu, Yulin Wang, Wei Li
To alleviate these issues, we propose to simultaneously conduct feature alignment in two individual spaces focusing on different domains, and create for each space a domain-oriented classifier tailored specifically for that domain.
1 code implementation • 29 Apr 2022 • Kaixiong Gong, Shuang Li, Shugang Li, Rui Zhang, Chi Harold Liu, Qiang Chen
We implement the findings and the alignment modules into our adaptation method, and it benchmarks the DETR-style detector on the domain shift settings.
no code implementations • 26 Apr 2022 • Zhenjie Yu, Kai Chen, Shuang Li, Bingfeng Han, Chi Harold Liu, Shuigen Wang
To be specific, ROMA could efficiently translate the unpaired nighttime infrared videos into fine-grained daytime visible ones, meanwhile maintain the spatiotemporal consistency via matching the cross-domain region similarity.
1 code implementation • 19 Apr 2022 • Binhui Xie, Shuang Li, Mingjia Li, Chi Harold Liu, Gao Huang, Guoren Wang
Domain adaptive semantic segmentation attempts to make satisfactory dense predictions on an unlabeled target domain by utilizing the supervised model trained on a labeled source domain.
Ranked #4 on Semantic Segmentation on GTAV-to-Cityscapes Labels
1 code implementation • CVPR 2022 • Fangrui Lv, Jian Liang, Shuang Li, Bin Zang, Chi Harold Liu, Ziteng Wang, Di Liu
Specifically, we assume that each input is constructed from a mix of causal factors (whose relationship with the label is invariant across domains) and non-causal factors (category-independent), and only the former cause the classification judgments.
1 code implementation • 17 Feb 2022 • Yinuo Zhao, Kun Wu, Zhiyuan Xu, Zhengping Che, Qi Lu, Jian Tang, Chi Harold Liu
Vision-based autonomous urban driving in dense traffic is quite challenging due to the complicated urban environment and the dynamics of the driving behaviors.
no code implementations • 18 Dec 2021 • Rui Han, Qinglong Zhang, Chi Harold Liu, Guoren Wang, Jian Tang, Lydia Y. Chen
The prior art sheds light on exploring the accuracy-resource tradeoff by scaling the model sizes in accordance to resource dynamics.
1 code implementation • NeurIPS 2021 • Fangrui Lv, Jian Liang, Kaixiong Gong, Shuang Li, Chi Harold Liu, Han Li, Di Liu, Guoren Wang
Domain adaptation (DA) attempts to transfer the knowledge from a labeled source domain to an unlabeled target domain that follows different distribution from the source.
1 code implementation • 2 Dec 2021 • Binhui Xie, Longhui Yuan, Shuang Li, Chi Harold Liu, Xinjing Cheng, Guoren Wang
Unsupervised domain adaptation has recently emerged as an effective paradigm for generalizing deep neural networks to new target domains.
1 code implementation • CVPR 2022 • Binhui Xie, Longhui Yuan, Shuang Li, Chi Harold Liu, Xinjing Cheng
Self-training has greatly facilitated domain adaptive semantic segmentation, which iteratively generates pseudo labels on unlabeled target data and retrains the network.
no code implementations • 25 Nov 2021 • Wenxuan Ma, Jinming Zhang, Shuang Li, Chi Harold Liu, Yulin Wang, Wei Li
Unsupervised Domain Adaptation (UDA) aims to transfer knowledge from a labeled source domain to an unlabeled target domain.
1 code implementation • ICCV 2021 • Shuang Li, Mixue Xie, Fangrui Lv, Chi Harold Liu, Jian Liang, Chen Qin, Wei Li
To tackle this issue, we propose Semantic Concentration for Domain Adaptation (SCDA), which encourages the model to concentrate on the most principal features via the pair-wise adversarial alignment of prediction distributions.
1 code implementation • 2 Aug 2021 • Shuang Li, Bingfeng Han, Zhenjie Yu, Chi Harold Liu, Kai Chen, Shuigen Wang
Human vision is often adversely affected by complex environmental factors, especially in night vision scenarios.
1 code implementation • CVPR 2021 • Tong Wu, Junshi Huang, Guangyu Gao, Xiaoming Wei, Xiaolin Wei, Xuan Luo, Chi Harold Liu
In inference, we directly use the activation masks from the DA layer as pseudo-labels for segmentation.
1 code implementation • 11 May 2021 • Shuang Li, Binhui Xie, Bin Zang, Chi Harold Liu, Xinjing Cheng, Ruigang Yang, Guoren Wang
Specifically, we first design a pixel-wise contrastive loss by considering the correspondences between semantic distributions and pixel-wise representations from both domains.
1 code implementation • CVPR 2021 • Shuang Li, Jinming Zhang, Wenxuan Ma, Chi Harold Liu, Wei Li
Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy.
1 code implementation • CVPR 2021 • Shuang Li, Mixue Xie, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Wei Li
To remedy this, we propose a Transferable Semantic Augmentation (TSA) approach to enhance the classifier adaptation ability through implicitly generating source features towards target semantics.
1 code implementation • CVPR 2021 • Shuang Li, Kaixiong Gong, Chi Harold Liu, Yulin Wang, Feng Qiao, Xinjing Cheng
Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the remaining minority classes.
Ranked #2 on Long-tail Learning on CIFAR-100-LT (ρ=200)
1 code implementation • 23 Mar 2021 • Shuang Li, Binhui Xie, Qiuxia Lin, Chi Harold Liu, Gao Huang, Guoren Wang
Domain Adaptation (DA) attempts to transfer knowledge learned in the labeled source domain to the unlabeled but related target domain without requiring large amounts of target supervision.
1 code implementation • 13 Dec 2020 • Shuang Li, Fangrui Lv, Binhui Xie, Chi Harold Liu, Jian Liang, Chen Qin
Motivated by the observation that target samples cannot always be separated distinctly by the decision boundary, here in the proposed BCDM, we design a novel classifier determinacy disparity (CDD) metric, which formulates classifier discrepancy as the class relevance of distinct target predictions and implicitly introduces constraint on the target feature discriminability.
1 code implementation • IEEE Transactions on Intelligent Transportation Systems 2020 • Yinuo Zhao, Chi Harold Liu
Vehicular crowdsensing (VCS) takes the advantage of vehicles’ mobility and exploits both the crowd wisdom and sensing abilities offered by vehicle drivers’ carried smart mobile devices and on-board sensors to accomplish challenging sensing tasks.
1 code implementation • 4 Aug 2020 • Shuang Li, Binhui Xie, Jiashu Wu, Ying Zhao, Chi Harold Liu, Zhengming Ding
In this paper, we propose a Simultaneous Semantic Alignment Network (SSAN) to simultaneously exploit correlations among categories and align the centroids for each category across domains.
1 code implementation • 14 May 2020 • Shuang Li, Chi Harold Liu, Qiuxia Lin, Binhui Xie, Zhengming Ding, Gao Huang, Jian Tang
Most existing deep DA models only focus on aligning feature representations of task-specific layers across domains while integrating a totally shared convolutional architecture for source and target.
1 code implementation • ICDE 2020 • Chi Harold Liu, Yinuo Zhao, Zipeng Dai, Ye Yuan, Guoren Wang, Dapeng Wu, Kin K. Leung
Spatial crowdsourcing (SC) utilizes the potential of a crowd to accomplish certain location based tasks.
1 code implementation • 10 Apr 2020 • Shuang Li, Chi Harold Liu, Qiuxia Lin, Qi Wen, Limin Su, Gao Huang, Zhengming Ding
Deep domain adaptation methods have achieved appealing performance by learning transferable representations from a well-labeled source domain to a different but related unlabeled target domain.
no code implementations • 17 Jan 2018 • Zhiyuan Xu, Jian Tang, Jingsong Meng, Weiyi Zhang, Yanzhi Wang, Chi Harold Liu, Dejun Yang
Modern communication networks have become very complicated and highly dynamic, which makes them hard to model, predict and control.