AI Paper Atlas

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

SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency

Yangyang Guo, Mohan Kankanhalli

ICCV 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Self-distillation for vision-language pretraining · 4 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
prune both redundant and ill-matched samples rather than redundant only (ablation)SCAN · ImageNet zero-shot (ViT-S/16)ZS@5: 33.51 -> 35.51Improved
prune both redundant and ill-matched samples rather than ill-matched only (ablation)SCAN · ImageNet zero-shot (ViT-S/16)ZS@5: 35.19 -> 35.51Improved
prune ill-matched samples alone instead of redundant alone (ablation)SCAN · ImageNet zero-shot (ViT-S/16)ZS@5: 33.51 -> 35.19Improved
use mutation epoch 3 instead of 4 (ablation)SCAN · ImageNet zero-shot (ViT-S/16)ZS@5: 33.80 -> 35.51Improved
use mutation epoch 3 instead of 2 (ablation)SCAN · ImageNet zero-shot (ViT-S/16)ZS@5: 36.28 -> 35.51Mixed
use 20:20 redundant to ill-matched ratio instead of 30:10 (ablation)SCAN · ImageNet zero-shot (ViT-S/16)ZS@5: 34.84 -> 35.51Improved
increase pruning ratio (ablation)SCAN · CLIP modelsdownstream accuracyHurt
use dynamic SCAN pruning instead of static SemDeDup coresetSCAN · ImageNet zero-shot (ViT-B/32)ZS@1: 07.20 -> 16.48Improved
use SCAN static coreset instead of SemDeDupSCAN · ImageNet zero-shot (ViT-B/32)ZS@1: 07.20 -> 13.16Improved
use SCAN (30% pruning) instead of full CLIP data on RN101SCAN · ImageNet fine-tune (CC3M+)top-1: 75.39 -> 74.61No clear effect
use SCAN instead of CLIP full data on Swin-BaseSCAN · ImageNet zero-shot (CC3M+)top-1: 13.98 -> 17.50Improved
use SCAN instead of Info-Batch on MoCo ViT-B/16SCAN · ImageNettop-1: 78.46 -> 79.15Improved

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