AI Paper Atlas

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

CASPA: Graph-Structured Concept Anchors for Modality-Agnostic Adaptation in Vision-Language Models

Abhiroop Chatterjee, Susmita Ghosh, Ashish Ghosh, Emmett Ientilucci

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Test-time adaptation of VLMs

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 text and image shift modules (ablation)CASPA · 4-shot ImageNet/Flowers/DTD (ViT-B/16)accuracy: 64.17 -> 70.28 (ImageNet)Improved
add anchors (K=0 -> K=48) (ablation)CASPA · DTD 4-shotaccuracy: 51.76 -> 65.43Improved
add cross-consistency regularization lambda_x (ablation)CASPA · 4-shot ImageNet/Flowers/DTD (ViT-B/16)accuracy: 64.36 -> 65.43 (DTD)Improved
cosine similarity instead of MSE for consistency (ablation)CASPA · 4-shot ImageNet/Flowers/DTD (ViT-B/16)accuracy: 64.15 -> 65.43 (DTD)Improved
add diversity regularizer lambda_d=0.05 (ablation)CASPA · 4-shot ImageNet/Flowers/DTD (ViT-B/16)accuracy: 65.11 -> 65.43 (DTD)Improved
increase anchors from 48 to 64 (ablation)CASPA · DTD 4-shotaccuracy: 65.43 -> 64.68Hurt
text shift only vs image shift only (ablation)CASPA · ImageNet (ViT-B/32), 1-8 shotaccuracy: 62.40 -> 65.30 (4-shot, image-only vs text-only)Improved
add ASAM optimizer (ablation)CASPA · EuroSAT Base-to-NovelNovel accuracy: 67.46% -> 82.06%Improved
raise adaptive scaling amax from 1 to 5-7 (ablation)CASPA · UCF Base-to-NovelNovel accuracy: 23.32% at 1 -> full potential at 5-7Improved
add CASPA-G on top of CoOp (ablation)CoOp · Base-to-Novel (11-dataset average)HM: 71.66 -> 77.98Improved
add Gaussian-weighted aggregation initialization (CASPA-A) (ablation)CASPA-G · Base-to-Novel (11-dataset average)HM: 81.01 -> 81.27Improved
anchor-based adapter vs RAdaCASPA-G · Base-to-Novel DTDHM: 73.86 -> 70.78Hurt

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