AI RESEARCH
Explaining CLIP Zero-shot Predictions Through Concepts
arXiv CS.CV
•
ArXi:2603.28211v1 Announce Type: new Large-scale vision-language models such as CLIP have achieved remarkable success in zero-shot image recognition, yet their predictions remain largely opaque to human understanding. In contrast, Concept Bottleneck Models provide interpretable intermediate representations by reasoning through human-defined concepts, but they rely on concept supervision and lack the ability to generalize to unseen classes. We