Local–Global Aware Concept Bottleneck Models for Interpretable Image Classification
Concept Bottleneck Models facilitate interpretable image classification by predicting human-understandable concepts prior to class labels. However, when constructed upon CLIP, they exhibit unreliable concept scores stemming from CLIP’s global representation bias and insufficient region-level sensiti...
Furkejuvvon:
| Váldodahkkit: | , , |
|---|---|
| Materiálatiipa: | Artigo |
| Giella: | Inglês |
| Almmustuhtton: |
MDPI AG
2026-03-01
|
| Ráidu: | Sensors |
| Fáttát: | |
| Liŋkkat: | https://www.mdpi.com/1424-8220/26/6/1833 |
| Fáddágilkorat: |
Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!
|