2 papers
cs.CV2025
Representation Calibration and Uncertainty Guidance for Class-Incremental Learning based on Vision Language Model
Jiantao Tan, Peixian Ma, Tong Yu +2
Class-incremental learning requires a learning system to continually learn knowledge of new classes and meanwhile try to preserve previously learned knowledge of old classes. As cu…
cs.CV2025
Augmenting Continual Learning of Diseases with LLM-Generated Visual Concepts
Jiantao Tan, Peixian Ma, Kanghao Chen +2
Continual learning is essential for medical image classification systems to adapt to dynamically evolving clinical environments. The integration of multimodal information can signi…