3 papers
cs.CV2025
Beyond Frequency: Seeing Subtle Cues Through the Lens of Spatial Decomposition for Fine-Grained Visual Classification
Qin Xu, Lili Zhu, Xiaoxia Cheng +1
The crux of resolving fine-grained visual classification (FGVC) lies in capturing discriminative and class-specific cues that correspond to subtle visual characteristics. Recently,…
cs.CV2025
Integrated Structural Prompt Learning for Vision-Language Models
Jiahui Wang, Qin Xu, Bo Jiang +1
Prompt learning methods have significantly extended the transferability of pre-trained Vision-Language Models (VLMs) like CLIP for various downstream tasks. These methods adopt han…
cs.CV2025
Dynamic Rank Adaptation for Vision-Language Models
Jiahui Wang, Qin Xu, Bo Jiang +1
Pre-trained large vision-language models (VLMs) like CLIP demonstrate impressive generalization ability. Existing prompt-based and adapter-based works have made significant progres…