AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding

Talfan Evans, Shreya Pathak, Hamza Merzic, Jonathan Richard Schwarz, Ryutaro Tanno, Olivier Henaff

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: Chain-of-thought multimodal reasoning · 17 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
prioritize high-loss data under the learner (hard learner) (ablation)ViT-B on JFT-300M · JFT-300Maccuracy / speedupNo clear effect
add a pretrained reference model (easy-reference or learnability scoring) (ablation)ViT-B on JFT-300M · JFT-300Mlearner speedup: speed-ups of ~33%Improved
use learnability instead of easy-reference scoring with small scoring models (ViT-S, ViT-Ti) (ablation)ViT-L on JFT-300M · JFT-300Mlearner speedup: 31% (ViT-B) -> 26% (ViT-Ti)Improved
scale down scoring models to ViT-Mu family (about 1000x smaller) (ablation)ClassAct · JFT-300M, ViT-Llearner speedup: 16% for the smallest actorsMixed
RHO with small reference model (ablation)ViT-B learner · JFT half, 3 epochslearner speedup: 0% learner speedup, - 79% compute speedupHurt
add small online model to scoring (ClassAct) instead of using the learner for scoring (ablation)RHO · JFT half, 3 epochscompute speedup: - 79% -> 3%Improved
train reference model online in parallel on larger super-batch (ablation)ClassAct · JFT half, 3 epochslearner speedup: 18% -> 17%No clear effect
reference model trained on held-out set instead of in-domain data (ablation)ClassAct · JFT half, 3 epochslearner speedup: 18% -> 18%No clear effect
use LTIP (cleaner) reference model instead of ALIGN reference (ablation)ActiveCLIP · ImageNet 0-shot, ALIGN learnertop-1 accuracy: 47.8 -> 53.2Improved
use ViT-Ti policy instead of ViT-B policy for ActiveCLIP (ablation)ActiveCLIP · ImageNet 0-shottop-1 accuracy / FLOP saving: 70.3 -> 69.9; FLOP saving -163.4% -> 26.2%Mixed
reference model trained on 350M curated Webli subset (ablation)ActiveSigLIP · Weblitransfer performanceImproved
apply ActiveSigLIP on top of SigLIPSigLIP · COCO retrieval and ImageNet 0-shotCOCO im2txt R@1: 60.7 -> 63.5 (im2txt), 42.7 -> 45.3 (txt2im), ImageNet 72.1 -> 72.0Mixed

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