Concept-wise Attention for Fine-grained Concept Bottleneck Models 事件

Concept-wise Attention for Fine-grained Concept Bottleneck Models arXiv:2604.15748v3 Announce Type: replace Abstract: Recently impressive performance has been achieved in Concept Bottleneck Models (CBM) by utilizing the image-text alignment learned by a large pre-trained vision-language model (i.e. CLIP). However, there exist two key limitations in concept modeling. Existing methods often suffer from pre-training biases, manifested as granularity misalignment or reliance on structural priors. M