Zhengyuan Xie — accepted AI-conference papers

2025

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery

Enguang Wang, Zhimao Peng, Zhengyuan Xie, Fei Yang, Xialei Liu, Ming-Ming Cheng

CVPR 2025poster

Given unlabelled datasets containing both old and new categories, generalized category discovery (GCD) aims to accurately discover new classes while correctly classifying old classes. Current GCD methods only use a single visual modality of information, resulting in poor classification of visually s…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2024

Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation

Zhengyuan Xie, Haiquan Lu, Jia-wen Xiao, Enguang Wang, Le Zhang, Xialei Liu*

ECCV 2024poster

"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…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗