7 papers
Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification
Kunlun Xu, Haotong Cheng, Jiangmeng Li +2
Lifelong person re-identification (LReID) aims to learn from varying domains to obtain a unified person retrieval model. Existing LReID approaches typically focus on learning from…
C^2Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning
Kunlun Xu, Yibo Feng, Jiangmeng Li +2
Federated continual learning (FCL) tackles scenarios of learning from continuously emerging task data across distributed clients, where the key challenge lies in addressing both te…
Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification
Kunlun Xu, Fan Zhuo, Jiangmeng Li +2
Current lifelong person re-identification (LReID) methods predominantly rely on fully labeled data streams. However, in real-world scenarios where annotation resources are limited,…
Componential Prompt-Knowledge Alignment for Domain Incremental Learning
Kunlun Xu, Xu Zou, Gang Hua +1
Domain Incremental Learning (DIL) aims to learn from non-stationary data streams across domains while retaining and utilizing past knowledge. Although prompt-based methods effectiv…
STOP: Integrated Spatial-Temporal Dynamic Prompting for Video Understanding
Zichen Liu, Kunlun Xu, Bing Su +3
Pre-trained on tremendous image-text pairs, vision-language models like CLIP have demonstrated promising zero-shot generalization across numerous image-based tasks. However, extend…
SCAP: Transductive Test-Time Adaptation via Supportive Clique-based Attribute Prompting
Chenyu Zhang, Kunlun Xu, Zichen Liu +2
Vision-language models (VLMs) encounter considerable challenges when adapting to domain shifts stemming from changes in data distribution. Test-time adaptation (TTA) has emerged as…