5 papers
Predictive Regularization Against Visual Representation Degradation in Multimodal Large Language Models
Enguang Wang, Qiang Wang, Yuanchen Wu +5
While Multimodal Large Language Models (MLLMs) excel at vision-language tasks, the cost of their language-driven training on internal visual foundational competence remains unclear…
Sharpness-aware Dynamic Anchor Selection for Generalized Category Discovery
Zhimao Peng, Enguang Wang, Fei Yang +2
Generalized category discovery (GCD) is an important and challenging task in open-world learning. Specifically, given some labeled data of known classes, GCD aims to cluster unlabe…
Predictive Sample Assignment for Semantically Coherent Out-of-Distribution Detection
Zhimao Peng, Enguang Wang, Xialei Liu +1
Semantically coherent out-of-distribution detection (SCOOD) is a recently proposed realistic OOD detection setting: given labeled in-distribution (ID) data and mixed in-distributio…
Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning
Xusheng Cao, Haori Lu, Linlan Huang +3
Continual learning in computer vision faces the critical challenge of catastrophic forgetting, where models struggle to retain prior knowledge while adapting to new tasks. Although…
GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery
Enguang Wang, Zhimao Peng, Zhengyuan Xie +3
Given unlabelled datasets containing both old and new categories, generalized category discovery (GCD) aims to accurately discover new classes while correctly classifying old class…