AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

CHIPS: Efficient CLIP Adaptation via Curvature-aware Hybrid Influence-based Data Selection

Xinlin Zhuang, Yichen Li, Xiwei Liu, Haolin Yang, Yifan Lu, Ziyun Zou, Yulong Li, Huifa Li, Dongliang Chen, Qinglei Wang, Weiyang Liu, Ying Qian and 2 more

CVPR 2026 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 0 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
select CPT data with CHIPS instead of random selectionMetaCLIP-B16-400M CPT on BIOMEDICA · Medical avg (17 tasks), r=10%avg accuracy: 24.78 -> 27.03Improved
use CHIPS instead of TracIn for selectionMetaCLIP-B16-400M CPT · Medical avg, r=10/20/30%avg accuracy: 26.46 -> 27.03; 26.63 -> 28.20; 25.68 -> 29.96Improved
CHIPS 30% subset instead of full-dataset CPTMetaCLIP-B16-400M CPT · Medical avgavg accuracy: 31.51 -> 29.96Hurt
CHIPS selection versus random on general-domain retentionMetaCLIP-B16-400M CPT · General CLS, r=10%classification accuracy: 52.21 (Random) -> 47.88 (CHIPS)Hurt
CHIPS instead of TracIn across seven backbones/scalesMetaCLIP B32/B16/L14/H14 (400M and CC) · Medical CLS, 10% keptaccuracy: e.g. L14-400M 27.08 -> 29.73Improved
add learnability margin term to alignment score (ablation)CHIPS · Medical avg, r=30%avg accuracy: 27.84 -> 28.50Improved
add learnability margin term to alignment score (ablation)CHIPS · Medical avg, r=10%avg accuracy: 25.98 -> 25.95No clear effect
add domain relevance weight on top of alignment+margin (ablation)CHIPS · Medical avg, r=10/20/30%avg accuracy: 25.95 -> 27.03; 27.92 -> 28.20; 28.50 -> 29.96Improved
restrict scoring subspace to text projection only versus all end-point params (ablation)CHIPS · Medical avg, r=10%avg accuracy: 27.03 -> 26.95No clear effect
score using only logit/temperature parameter (ablation)CHIPS · Medical avg, r=10%avg accuracy: 27.03 -> 23.83Hurt
increase target eval set size from 50 to 200 samples per task (ablation)CHIPS · Medical avg, r=10%avg accuracy: 26.25 -> 27.03Improved
mix negative-pair curvature at moderate alpha (0.6-0.8) vs extremes (ablation)CHIPS · Medical avg, r=10%avg accuracy: 25.66 (alpha 0.4) / 26.07 (alpha 1.0) -> 27.05 (alpha 0.6)Improved

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