AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Concepts

Andong Tan, Fengtao Zhou, Hao Chen

ECCV 2024 · Vision-language and multimodal › CLIP and zero-shot · approach: Language models for zero-shot reasoning · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
align trainable feature extractor to CLIP class prototypesOpenCBM (ResNet18) · CUB-200-2011accuracy %: 74.3 -> 83.3 vs Label-free CBMImproved
train feature extractor with prototype alignment instead of frozen CLIP linear probing (ablation)CLIP-RN50 · CUB-200-2011accuracy %: 75.5 -> 83.3Improved
use class-prototype alignment instead of sample-wise alignment (ablation)OpenCBM · CUB-200-2011accuracy %: 79.8 -> 81.8Improved
increase alignment loss weight beta2 from 1 to 5 (ablation)OpenCBM · CUB-200-2011accuracy %: 81.8 -> 83.3Improved
add more concepts (5% to 20% of LaBO concept set) (ablation)OpenCBM · CUB-200-2011accuracy %: 44.1 -> 82.94Improved
remove the class name as a concept from unknown concept set (ablation)OpenCBM · CUB-200-2011classes with accuracy drop: 173.6±4.3 out of 200Improved
add concepts to the original 3-per-class set (5 per class) (ablation)OpenCBM · CUB-200-2011 class yellow breasted chatclass accuracy %: 50 -> 94.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy