AI Paper Atlas

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

Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Model

Shiming Chen, Bowen Duan, Salman Khan, Fahad Shahbaz Khan

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Adapting VLMs for zero-shot classification · 6 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
add OT local visual-semantic alignment to DCLIP baseline (ablation)DCLIP (CLIP ViT-B/16) · ImageNetaccuracy: 67.9 -> 68.5Improved
add OT local visual-semantic alignment to DCLIP baseline (ablation)DCLIP (CLIP ViT-B/16) · CUBaccuracy: 57.8 -> 59.0Improved
add OT local visual-semantic alignment to DCLIP baseline (ablation)DCLIP (CLIP ViT-B/16) · Place365accuracy: 40.3 -> 41.6Improved
add vision selection on top of OT (ablation)Baseline+OT (CLIP ViT-B/16) · CUBaccuracy: 59.0 -> 60.0Improved
add vision selection on top of OT (ablation)Baseline+OT (CLIP ViT-B/16) · ImageNetaccuracy: 68.5 -> 69.0Improved
add region-global hybrid cost on top of OT (ablation)Baseline+OT (CLIP ViT-B/16) · CUBaccuracy: 59.0 -> 59.3Improved
add region-global hybrid cost on top of OT (ablation)Baseline+OT (CLIP ViT-B/16) · Place365accuracy: 41.6 -> 41.9Improved
add hybrid cost to OT+VS (full LaZSL) (ablation)Baseline+OT+VS (CLIP ViT-B/16) · CUBaccuracy: 60.0 -> 60.3Improved
LaZSL versus DCLIP across backbonesDCLIP · five-dataset averageaccuracy: +2.0 (B/32), +1.6 (B/16), +1.2 (L/14)Improved
LaZSL versus CuPL on ImageNet and Oxford Pets with ViT-B/16CuPL · ImageNetaccuracy: 69.6 -> 69.2Hurt
set hybrid coefficient theta too high (>=0.9) (ablation)LaZSL · CUB and ImageNetaccuracyHurt
set cropping scale alpha too large (>=0.6) (ablation)LaZSL · CUB and ImageNetaccuracyHurt

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