2 citations · 2 across the 5 of their papers we have counts for
6 papers
DVTR-KD: Distilling Vision-Language Models via Intermediate Visual Token Reconstruction
Haolan Wei, Jiahui Wang, Junli Zha +4
Multimodal large language models (MLLMs) have achieved strong performance on diverse vision-language tasks, but their computational demands limit deployment under constrained budge…
Illusion-Aware Visual Preprocessing and Anti-Illusion Prompting for Classic Illusion Understanding in Vision-Language Models
Junli Zha, Jiahui Wang, Xinkai Lu +1
Vision-Language Models (VLMs) exhibit systematic bias toward visual illusions, recalling memorized facts rather than perceiving actual visual differences. This paper presents a tra…
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…
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…
Context-Semantic Quality Awareness Network for Fine-Grained Visual Categorization
Qin Xu, Sitong Li, Jiahui Wang +2
Exploring and mining subtle yet distinctive features between sub-categories with similar appearances is crucial for fine-grained visual categorization (FGVC). However, less effort…
Robust Transductive Few-shot Learning via Joint Message Passing and Prototype-based Soft-label Propagation
Jiahui Wang, Qin Xu, Bo Jiang +1
Few-shot learning (FSL) aims to develop a learning model with the ability to generalize to new classes using a few support samples. For transductive FSL tasks, prototype learning a…