Yixin Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yixin Zhang has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Zilei Wang
University of Science and Technology of China, Hefei, China
8 shared publications - Junjie Li
Beijing University of Posts and Telecommunications, Haidian, Beijing, China
2 shared publications - Man Zhang
Beijing University of Posts and Telecommunications
2 shared publications - Cerui Dong
National Engineering Laboratory for Brain-inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, 230026, China
1 shared publication - Feng Zhao
MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China
1 shared publication - Gaoxiang Li
Beijing Normal University, Beijing, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4817-4825
Restoring Semantic Fidelity for Training-Free High-Resolution Image Generation in Diffusion Transformers
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 4817-4825
Open AccessRestoring Semantic Fidelity for Training-Free High-Resolution Image Generation in Diffusion Transformers
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2778-2785
Ray-Match: Ray-aware One-to-many Training Strategy for Multi-View 3D Object Detection
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2778-2785
Open AccessRay-Match: Ray-aware One-to-many Training Strategy for Multi-View 3D Object Detection
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11700-11708
ReliaPose: Closing the Loop of Reliability-Aware Temporal Fusion for Video Pose Estimation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 11700-11708
Open AccessReliaPose: Closing the Loop of Reliability-Aware Temporal Fusion for Video Pose Estimation
- 22 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (2) , 2304-2317
Improving Zero-Shot Generalization for CLIP With Prompt Ensemble Self-Distillation
Prompt tuning has emerged as an effective alternative for adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks. In our experiments utilizing prompt tuning methods, we observed that modifying the prompt initialization led to inconsistencies in the model’s predictions, particularly with pronounced variability on specific datasets. Motivated by this observation, we examine the predictive performance of two ensemble methods: prompt fusion and logits fusion. Experimental results indicate that logits fusion results in considerable performance improvements, while prompt fusion does not yield any enhancements. However, a significant downside of logits fusion is the enormous rise in inference time. To investigate a practical approach for integrating knowledge derived from multiple prompts without incurring additional inference costs, we propose a straightforward Prompt Ensemble self-Distillation (PED) framework that considerably improves the generalization capacity of prompt tuning. Specifically, we initialize multiple groups of prompts, and during the training process, we integrate the prediction outputs from each group to facilitate the learning of the fused prompts. The proposed self-distillation approach offers dual benefits: enhancing the performance of both the fused prompts and the fused logits. We utilize fused prompts for prediction during the inference process, thereby achieving performance that is comparable to that of fused logits without incurring additional inference time. We evaluate the effectiveness of our methodology across four distinct tasks. Our PED consistently demonstrates superior performance in all assessments when contrasted with numerous state-of-the-art methods. Moreover, our method can be seamlessly integrated into existing prompt learning approaches and consistently improves their performance. Our code is publicly available at https://github.com/vim-wei/PED.
- 22 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (2) , 2304-2317
Improving Zero-Shot Generalization for CLIP With Prompt Ensemble Self-Distillation
Prompt tuning has emerged as an effective alternative for adapting pre-trained Vision-Language Models (VLMs) to various downstream tasks. In our experiments utilizing prompt tuning methods, we observed that modifying the prompt initialization led to inconsistencies in the model’s predictions, particularly with pronounced variability on specific datasets. Motivated by this observation, we examine the predictive performance of two ensemble methods: prompt fusion and logits fusion. Experimental results indicate that logits fusion results in considerable performance improvements, while prompt fusion does not yield any enhancements. However, a significant downside of logits fusion is the enormous rise in inference time. To investigate a practical approach for integrating knowledge derived from multiple prompts without incurring additional inference costs, we propose a straightforward Prompt Ensemble self-Distillation (PED) framework that considerably improves the generalization capacity of prompt tuning. Specifically, we initialize multiple groups of prompts, and during the training process, we integrate the prediction outputs from each group to facilitate the learning of the fused prompts. The proposed self-distillation approach offers dual benefits: enhancing the performance of both the fused prompts and the fused logits. We utilize fused prompts for prediction during the inference process, thereby achieving performance that is comparable to that of fused logits without incurring additional inference time. We evaluate the effectiveness of our methodology across four distinct tasks. Our PED consistently demonstrates superior performance in all assessments when contrasted with numerous state-of-the-art methods. Moreover, our method can be seamlessly integrated into existing prompt learning approaches and consistently improves their performance. Our code is publicly available at https://github.com/vim-wei/PED.
- 24 January 2025
- Published by Elsevier in Neural Networks
- Vol. 185, 107140
Context Sensitive Network for weakly-supervised fine-grained temporal action localization
- 24 January 2025
- Published by Elsevier in Neural Networks
- Vol. 185, 107140
Context Sensitive Network for weakly-supervised fine-grained temporal action localization
- Open Access
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 2, 1001-1009
Probabilistic Contrastive Learning for Domain Adaptation
Contrastive learning has shown impressive success in enhancing feature discriminability for various visual tasks in a self-supervised manner, but the standard contrastive paradigm (features+l2 normalization) has limited benefits when applied in domain adaptation. We find that this is mainly because the class weights (weights of the final fully connected layer) are ignored in the domain adaptation optimization process, which makes it difficult for features to cluster around the corresponding class weights. To solve this problem, we propose the simple but powerful Probabilistic Contrastive Learning (PCL), which moves beyond the standard paradigm by removing l2 normalization and replacing the features with probabilities. PCL can guide the probability distribution towards a one-hot configuration, thus minimizing the discrepancy between features and class weights. We conduct extensive experiments to validate the effectiveness of PCL and observe consistent performance gains on five tasks, i.e., Unsupervised/Semi-Supervised Domain Adaptation (UDA/SSDA), Semi-Supervised Learning (SSL), UDA Detection and Semantic Segmentation. Notably, for UDA Semantic Segmentation on SYNTHIA, PCL surpasses the sophisticated CPSL-D by 2% in terms of mean IoU with a much lower training cost (PCL: 1*3090, 5 days v.s. CPSL-D: 4*V100, 11 days). Code is available at https://github.com/ljjcoder/Probabilistic-Contrastive-Learning.
- 1 August 2024
- Published by International Joint Conferences on Artificial Intelligence
- Vol. 2, 1001-1009
Open AccessProbabilistic Contrastive Learning for Domain Adaptation
Contrastive learning has shown impressive success in enhancing feature discriminability for various visual tasks in a self-supervised manner, but the standard contrastive paradigm (features+l2 normalization) has limited benefits when applied in domain adaptation. We find that this is mainly because the class weights (weights of the final fully connected layer) are ignored in the domain adaptation optimization process, which makes it difficult for features to cluster around the corresponding class weights. To solve this problem, we propose the simple but powerful Probabilistic Contrastive Learning (PCL), which moves beyond the standard paradigm by removing l2 normalization and replacing the features with probabilities. PCL can guide the probability distribution towards a one-hot configuration, thus minimizing the discrepancy between features and class weights. We conduct extensive experiments to validate the effectiveness of PCL and observe consistent performance gains on five tasks, i.e., Unsupervised/Semi-Supervised Domain Adaptation (UDA/SSDA), Semi-Supervised Learning (SSL), UDA Detection and Semantic Segmentation. Notably, for UDA Semantic Segmentation on SYNTHIA, PCL surpasses the sophisticated CPSL-D by 2% in terms of mean IoU with a much lower training cost (PCL: 1*3090, 5 days v.s. CPSL-D: 4*V100, 11 days). Code is available at https://github.com/ljjcoder/Probabilistic-Contrastive-Learning.
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5370-5379
Exploiting Low-confidence Pseudo-labels for Source-free Object Detection
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5370-5379
Open AccessExploiting Low-confidence Pseudo-labels for Source-free Object Detection
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5645-5654
Semi-supervised Domain Adaptation via Joint Contrastive Learning with Sensitivity
Semi-supervised Domain Adaptation (SSDA) aims to learn a well-performed model using fully labeled source samples and scarcely labeled target samples, along with unlabeled target samples. Due to the dominant presence of labeled samples from the source domain in the training data, both the feature extractor and classifier can display bias towards the source domain. This can result in sub-optimal feature extraction for the challenging target samples that have notable differences from the source domain. Moreover, the source-favored classifier can hinder the classification performance of the target domain. To this end, we propose a novel Joint Contrastive Learning with Sensitivity (JCLS) in this paper, which consists of sensitivity-aware feature contrastive learning (SFCL) and class-wise probabilistic contrastive learning (CPCL). Different from the traditional contrastive learning, SFCL pays more attention to the sensitive samples during optimizing the feature extractor, and consequently the feature discrimination of unlabeled samples can be enhanced. CPCL performs class-wise contrastive learning in the probabilistic space to enforce the cross-domain classifier to match the real distribution of source and target samples. By combining these two components, our JCLS is able to extract domain-invariant and compact features and obtain a well-performed classifier. We conduct the experiments on the DomainNet and Office-Home benchmarks, and the results show that our approach achieves state-of-the-art performance.
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 5645-5654
Open AccessSemi-supervised Domain Adaptation via Joint Contrastive Learning with Sensitivity
Semi-supervised Domain Adaptation (SSDA) aims to learn a well-performed model using fully labeled source samples and scarcely labeled target samples, along with unlabeled target samples. Due to the dominant presence of labeled samples from the source domain in the training data, both the feature extractor and classifier can display bias towards the source domain. This can result in sub-optimal feature extraction for the challenging target samples that have notable differences from the source domain. Moreover, the source-favored classifier can hinder the classification performance of the target domain. To this end, we propose a novel Joint Contrastive Learning with Sensitivity (JCLS) in this paper, which consists of sensitivity-aware feature contrastive learning (SFCL) and class-wise probabilistic contrastive learning (CPCL). Different from the traditional contrastive learning, SFCL pays more attention to the sensitive samples during optimizing the feature extractor, and consequently the feature discrimination of unlabeled samples can be enhanced. CPCL performs class-wise contrastive learning in the probabilistic space to enforce the cross-domain classifier to match the real distribution of source and target samples. By combining these two components, our JCLS is able to extract domain-invariant and compact features and obtain a well-performed classifier. We conduct the experiments on the DomainNet and Office-Home benchmarks, and the results show that our approach achieves state-of-the-art performance.
- 22 October 2022
- Published by Springer Nature
- p. 345-361
Continual Semantic Segmentation via Structure Preserving and Projected Feature Alignment
- 22 October 2022
- Published by Springer Nature
- p. 345-361
Continual Semantic Segmentation via Structure Preserving and Projected Feature Alignment