Kecheng Zheng
Kecheng Zheng has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Zheng-Jun Zha
University of Science and Technology of China, Hefei, China
3 shared publications - Bingyu Hu
University of Science and Technology of China, Hefei, China
2 shared publications - Jiawei Liu
University of Science and Technology of China
2 shared publications - Bin Huang
Department of Computer Science and Technology, Tsinghua University, Beijing, China
1 shared publication - Ceyuan Yang
Shanghai AI Laboratory
1 shared publication - Fan Cheng
School of Cryptology, East China Normal University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1413-1422
Reflective Cross-Granularity Grounding with Preference Optimization for Long Video Understanding
- 15 June 2026
- Published by Association for Computing Machinery (ACM)
- p. 1413-1422
Open AccessReflective Cross-Granularity Grounding with Preference Optimization for Long Video Understanding
- 3 June 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (11) , 5124-5150
Exert Diversity and Mitigate Bias: Domain Generalizable Person Re-identification with a Comprehensive Benchmark
- 3 June 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (11) , 5124-5150
Exert Diversity and Mitigate Bias: Domain Generalizable Person Re-identification with a Comprehensive Benchmark
- 15 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 5422-5434
Unleashing Knowledge Potential of Source Hypothesis for Source-Free Domain Adaptation
S ource- F ree D omain A daptation (SFDA) task aims to transfer knowledge from a labeled source domain to a label-scarce target domain, in which the source data can not be accessed but only a pre-trained source model and unlabeled target data are available during adaptation. Previous methods for source model adaptation rely on hypothesis transfer learning that trains the feature extractor to learn target features aligned to the distribution of source features while freezing the source classifier. However, reusing only the source classifier without exploring the comprehensive knowledge of the source model can lead to biased feature alignment. To this end, we propose a novel method called Transformer-bAsed thorouGh Source HypOthesis Transfer (TagSHOT) framework to effectively unleash the thorough knowledge potential of pre-trained source hypothesis. Specifically, our approach delves into the correlation coefficient among CLS/patch tokens across different Transformer layers, uncovering the concealed insights within the pre-trained source model and constructing a comprehensive source hypothesis. By tailoring the target feature alignment to this thorough source hypothesis, our model facilitates the adaptation of a broader range of classification-related knowledge to the target domain. Furthermore, we introduce a Salient Token Extension (STE) module, designed to capture the target-specific discriminative information by propagating the salient information among tokens. This mechanism enriches our model's ability to understand and incorporate target-specific nuances. Extensive experiments have been conducted to validate the effectiveness of our method, which outperforms state-of-the-art approaches by a large margin.
- 15 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 5422-5434
Unleashing Knowledge Potential of Source Hypothesis for Source-Free Domain Adaptation
S ource- F ree D omain A daptation (SFDA) task aims to transfer knowledge from a labeled source domain to a label-scarce target domain, in which the source data can not be accessed but only a pre-trained source model and unlabeled target data are available during adaptation. Previous methods for source model adaptation rely on hypothesis transfer learning that trains the feature extractor to learn target features aligned to the distribution of source features while freezing the source classifier. However, reusing only the source classifier without exploring the comprehensive knowledge of the source model can lead to biased feature alignment. To this end, we propose a novel method called Transformer-bAsed thorouGh Source HypOthesis Transfer (TagSHOT) framework to effectively unleash the thorough knowledge potential of pre-trained source hypothesis. Specifically, our approach delves into the correlation coefficient among CLS/patch tokens across different Transformer layers, uncovering the concealed insights within the pre-trained source model and constructing a comprehensive source hypothesis. By tailoring the target feature alignment to this thorough source hypothesis, our model facilitates the adaptation of a broader range of classification-related knowledge to the target domain. Furthermore, we introduce a Salient Token Extension (STE) module, designed to capture the target-specific discriminative information by propagating the salient information among tokens. This mechanism enriches our model's ability to understand and incorporate target-specific nuances. Extensive experiments have been conducted to validate the effectiveness of our method, which outperforms state-of-the-art approaches by a large margin.
- Open Access
Abstract Reasoning with Distracting Features
Abstraction reasoning is a long-standing challenge in artificial intelligence. Recent studies suggest that many of the deep architectures that have triumphed over other domains failed to work well in abstract reasoning. In this paper, we first illustrate that one of the main challenges in such a reasoning task is the presence of distracting features, which requires the learning algorithm to leverage counterevidence and to reject any of the false hypotheses in order to learn the true patterns. We later show that carefully designed learning trajectory over different categories of training data can effectively boost learning performance by mitigating the impacts of distracting features. Inspired by this fact, we propose feature robust abstract reasoning (FRAR) model, which consists of a reinforcement learning based teacher network to determine the sequence of training and a student network for predictions. Experimental results demonstrated strong improvements over baseline algorithms and we are able to beat the state-of-the-art models by 18.7% in the RAVEN dataset and 13.3% in the PGM dataset.
Open AccessAbstract Reasoning with Distracting Features
Abstraction reasoning is a long-standing challenge in artificial intelligence. Recent studies suggest that many of the deep architectures that have triumphed over other domains failed to work well in abstract reasoning. In this paper, we first illustrate that one of the main challenges in such a reasoning task is the presence of distracting features, which requires the learning algorithm to leverage counterevidence and to reject any of the false hypotheses in order to learn the true patterns. We later show that carefully designed learning trajectory over different categories of training data can effectively boost learning performance by mitigating the impacts of distracting features. Inspired by this fact, we propose feature robust abstract reasoning (FRAR) model, which consists of a reinforcement learning based teacher network to determine the sequence of training and a student network for predictions. Experimental results demonstrated strong improvements over baseline algorithms and we are able to beat the state-of-the-art models by 18.7% in the RAVEN dataset and 13.3% in the PGM dataset.