12 papers
BPG: Balancing Plasticity and Generalization for Domain Incremental Learning
Qiang Wang, Songlin Dong, Shaokun Wang +5
Deep neural networks excel in various tasks but struggle to generalize across evolving data distributions, leading to significant performance degradation under domain shifts. Domai…
LPT: Less-overfitting Prompt Tuning for Vision-Language Model
Chenhao Ding, Xinyuan Gao, Songlin Dong +5
Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more eff…
StructAlign: Structured Cross-Modal Alignment for Continual Text-to-Video Retrieval
Shaokun Wang, Weili Guan, Jizhou Han +3
Continual Text-to-Video Retrieval (CTVR) is a challenging multimodal continual learning setting, where models must incrementally learn new semantic categories while maintaining acc…
Unleashing the Potential of All Test Samples: Mean-Shift Guided Test-Time Adaptation
Jizhou Han, Chenhao Ding, SongLin Dong +3
Visual-language models (VLMs) like CLIP exhibit strong generalization but struggle with distribution shifts at test time. Existing training-free test-time adaptation (TTA) methods…
Learning Like Humans: Analogical Concept Learning for Generalized Category Discovery
Jizhou Han, Chenhao Ding, Yuhang He +4
Generalized Category Discovery (GCD) seeks to uncover novel categories in unlabeled data while preserving recognition of known categories, yet prevailing visual-only pipelines and…
GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery
Jizhou Han, Chenhao Ding, SongLin Dong +4
Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typic…