AI Paper Atlas

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

Low-Shot Validation: Active Importance Sampling for Estimating Classifier Performance on Rare Categories

Fait Poms, Vishnu Sarukkai, Ravi Teja Mullapudi, Nimit S. Sohoni, William R. Mark, Deva Ramanan, Kayvon Fatahalian

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 7 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
add calibration (isotonic) to importance sampling (ablation)SAWADE importance sampling · ImageNet50KF1 MSEImproved
add active importance sampling to calibration (ablation)ISO / PLATT calibration-only · ImageNet50KF1 MSEImproved
average estimates over last iterations instead of last only (ablation)ACIS-LAST · ImageNet50KF1 MSE: fewer than 100 samplesImproved
use isotonic regression instead of Platt scaling (ablation)ACIS · ImageNet50KF1 MSEImproved
calibration-only sampling at uniform random vs pure random (ablation)ISO, PLATT vs RAND · ImageNet50KF1 MSE: <100 samplesNo clear effect
restrict sampling to adaptive top-K scored examples (ablation)ACIS · rare categoriesF1 MSEImproved
average per-iteration variances instead of worst-case covariance 1 (ablation)ACIS variance estimate · ImageNet1Mvariance estimate accuracyImproved
validate other models with sets curated for a different modelACIS validation sets · ImageNet50KF1 MSE: at most double the MSE of the model-specific estimatorMixed
raise classifier threshold from 0.1-curated set to higher thresholdsACIS validation set transfer · ImageNet50KF1 MSE: thresholds 0.02 to 0.5Hurt

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