Zhengyuan Xie
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Zhengyuan Xie has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Xialei Liu
Nankai University
4 shared publications - Enguang Wang
VCIP, College of Computer Science, Nankai University, Tianjin, China
2 shared publications - Fei Yang
Nankai University
2 shared publications - Haiquan Lu
National University of Singapore
2 shared publications Enguang Wang
VCIP CS Nankai University
1 shared publication- Enguang Wang
Nankai University
1 shared publication
Latest Publications
- 11 September 2026
- Published by Springer Nature
- p. 172-190
Task-Agnostic Incremental Vision-Language Object Detection via Prompt Augmentation and Distribution-Aware Fusion
- 11 September 2026
- Published by Springer Nature
- p. 172-190
Task-Agnostic Incremental Vision-Language Object Detection via Prompt Augmentation and Distribution-Aware Fusion
- Open Access
Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery
Generalized Category Discovery (GCD) aims to classify unlabeled data containing both seen and novel categories. Although existing methods perform well on generic datasets, they struggle in fine-grained scenarios. We attribute this difficulty to their reliance on contrastive learning over global image features to automatically capture discriminative cues, which fails to capture the subtle local differences essential for distinguishing fine-grained categories. Therefore, in this paper, we propose incorporating part knowledge to address fine-grained GCD, which introduces two key challenges: the absence of annotations for novel classes complicates the extraction of the part features, and global contrastive learning prioritizes holistic feature invariance, inadvertently suppressing discriminative local part patterns. To address these challenges, we propose PartGCD, including 1) Adaptive Part Decomposition, which automatically extracts class-specific semantic parts via Gaussian Mixture Models, and 2) Part Discrepancy Regularization, enforcing explicit separation between part features to amplify fine-grained local part distinctions. Experiments demonstrate state-of-the-art performance across multiple fine-grained benchmarks while maintaining competitiveness on generic datasets, validating the effectiveness and robustness of our approach.
Open AccessLearning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery
Generalized Category Discovery (GCD) aims to classify unlabeled data containing both seen and novel categories. Although existing methods perform well on generic datasets, they struggle in fine-grained scenarios. We attribute this difficulty to their reliance on contrastive learning over global image features to automatically capture discriminative cues, which fails to capture the subtle local differences essential for distinguishing fine-grained categories. Therefore, in this paper, we propose incorporating part knowledge to address fine-grained GCD, which introduces two key challenges: the absence of annotations for novel classes complicates the extraction of the part features, and global contrastive learning prioritizes holistic feature invariance, inadvertently suppressing discriminative local part patterns. To address these challenges, we propose PartGCD, including 1) Adaptive Part Decomposition, which automatically extracts class-specific semantic parts via Gaussian Mixture Models, and 2) Part Discrepancy Regularization, enforcing explicit separation between part features to amplify fine-grained local part distinctions. Experiments demonstrate state-of-the-art performance across multiple fine-grained benchmarks while maintaining competitiveness on generic datasets, validating the effectiveness and robustness of our approach.
- 29 October 2024
- Published by Springer Nature
- p. 183-201
Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation
- 29 October 2024
- Published by Springer Nature
- p. 183-201
Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation
- Open Access
Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation
Class incremental semantic segmentation aims to preserve old knowledge while learning new tasks, however, it is impeded by catastrophic forgetting and background shift issues. Prior works indicate the pivotal importance of initializing new classifiers and mainly focus on transferring knowledge from the background classifier or preparing classifiers for future classes, neglecting the flexibility and variance of new classifiers. In this paper, we propose a new classifier pre-tuning~(NeST) method applied before the formal training process, learning a transformation from old classifiers to generate new classifiers for initialization rather than directly tuning the parameters of new classifiers. Our method can make new classifiers align with the backbone and adapt to the new data, preventing drastic changes in the feature extractor when learning new classes. Besides, we design a strategy considering the cross-task class similarity to initialize matrices used in the transformation, helping achieve the stability-plasticity trade-off. Experiments on Pascal VOC 2012 and ADE20K datasets show that the proposed strategy can significantly improve the performance of previous methods. The code is available at \url{https://github.com/zhengyuan-xie/ECCV24_NeST}.
Open AccessEarly Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation
Class incremental semantic segmentation aims to preserve old knowledge while learning new tasks, however, it is impeded by catastrophic forgetting and background shift issues. Prior works indicate the pivotal importance of initializing new classifiers and mainly focus on transferring knowledge from the background classifier or preparing classifiers for future classes, neglecting the flexibility and variance of new classifiers. In this paper, we propose a new classifier pre-tuning~(NeST) method applied before the formal training process, learning a transformation from old classifiers to generate new classifiers for initialization rather than directly tuning the parameters of new classifiers. Our method can make new classifiers align with the backbone and adapt to the new data, preventing drastic changes in the feature extractor when learning new classes. Besides, we design a strategy considering the cross-task class similarity to initialize matrices used in the transformation, helping achieve the stability-plasticity trade-off. Experiments on Pascal VOC 2012 and ADE20K datasets show that the proposed strategy can significantly improve the performance of previous methods. The code is available at \url{https://github.com/zhengyuan-xie/ECCV24_NeST}.