AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Agile Modeling: From Concept to Classifier in Minutes

Otilia Stretcu, Edward Vendrow, Kenji Hata, Krishnamurthy Viswanathan, Vittorio Ferrari, Sasan Tavakkol, Wenlei Zhou, Aditya Avinash, Emming Luo, Neil Gordon Alldrin, MohammadHossein Bateni, Gabriel Berger and 6 more

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Loss design and classifier theory · 13 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
train supervised model on user ratings instead of zero-shot scoring (a few more minutes of rating)Agile Modeling · User study, 14 conceptsAUC PR: +3% after 5 minutes, +16% after 24 minutesImproved
initial model trained on only 100 images vs zero-shot, CLIP embeddingsAgile Modeling · User study, 14 conceptsAUC PRHurt
label with the user instead of crowd raters on hard concepts (ablation)Agile Modeling · Hard concepts, CLIP embeddingsAUC PR: User-100 above Crowd-500Improved
use margin plus positive mining instead of plain margin active learning (ablation)Agile Modeling · User study, 14 conceptsAUC PRNo clear effect
use smaller active learning batch size (50 vs 100 vs 200) at fixed rating budget (ablation)Agile Modeling · User study, 14 conceptsAUC PRImproved
use ALIGN instead of CLIP embeddings (ablation)Agile Modeling · User study, final modelAUPR: 0.68 -> 0.76Improved
use ALIGN instead of CLIP embeddings (ablation)Agile Modeling · User study, final modelAUROC: 0.72 -> 0.80Improved
apply Agile Modeling with simulated users on 100 ImageNet21k conceptsAgile Modeling · ImageNet21k, 100 conceptsAUC PR: +20% over zero-shotImproved

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