4 papers
Rethinking the Sample Relations for Few-Shot Classification
Guowei Yin, Sheng Huang, Luwen Huangfu +2
Feature quality is paramount for classification performance, particularly in few-shot scenarios. Contrastive learning, a widely adopted technique for enhancing feature quality, lev…
Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification
Jiexuan Yan, Sheng Huang, Nankun Mu +2
Real-world data consistently exhibits a long-tailed distribution, often spanning multiple categories. This complexity underscores the challenge of content comprehension, particular…
SAM-MIL: A Spatial Contextual Aware Multiple Instance Learning Approach for Whole Slide Image Classification
Heng Fang, Sheng Huang, Wenhao Tang +2
Multiple Instance Learning (MIL) represents the predominant framework in Whole Slide Image (WSI) classification, covering aspects such as sub-typing, diagnosis, and beyond. Current…
Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognition
Yijie Wang, Mingjian Hong, Luwen Huangfu +1
In the realm of Zero-Shot Learning (ZSL), we address biases in Generalized Zero-Shot Learning (GZSL) models, which favor seen data. To counter this, we introduce an end-to-end gene…