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...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Ci Liu, Zijie Lin, Chen Tang
Format:	Artigo
Sprog:	Inglês
Udgivet:	MDPI AG 2026-03-01
Serier:	Sensors
Fag:	interpretable artificial intelligence concept bottleneck models image classification few-shot learning
Online adgang:	https://www.mdpi.com/1424-8220/26/6/1833
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!