5 papers
Complementary Text-Guided Attention for Zero-Shot Adversarial Robustness
Lu Yu, Haiyang Zhang, Changsheng Xu
Due to the impressive zero-shot capabilities, pre-trained vision-language models (e.g., CLIP), have attracted widespread attention and adoption across various domains. Nonetheless,…
Exploiting the Semantic Knowledge of Pre-trained Text-Encoders for Continual Learning
Lu Yu, Zhe Tao, Dipam Goswami +4
Deep neural networks (DNNs) excel on fixed datasets but struggle with incremental and shifting data in real-world scenarios. Continual learning addresses this challenge by allowing…
Locality Preserving Markovian Transition for Instance Retrieval
Jifei Luo, Wenzheng Wu, Hantao Yao +2
Diffusion-based re-ranking methods are effective in modeling the data manifolds through similarity propagation in affinity graphs. However, positive signals tend to diminish over s…
Language Guided Concept Bottleneck Models for Interpretable Continual Learning
Lu Yu, Haoyu Han, Zhe Tao +2
Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating…
SEP: Self-Enhanced Prompt Tuning for Visual-Language Model
Hantao Yao, Rui Zhang, Lu Yu +2
Prompt tuning based on Context Optimization (CoOp) effectively adapts visual-language models (VLMs) to downstream tasks by inferring additional learnable prompt tokens. However, th…