AI Paper Atlas

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

AutoEval: Are Labels Always Necessary for Classifier Accuracy Evaluation?

Weijian Deng, Liang Zheng

TPAMI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Group-robust classification · 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
replace confidence-threshold prediction (tau=0.7) with neural network regression on dataset statisticspredicted score method · Digits (SVHN+USPS)RMSE (%): 18.11 -> 1.46Improved
replace linear regression with neural network regression using mean and covariance featureslinear regression · Digits (SVHN+USPS)RMSE (%): 9.87 -> 1.46Improved
replace linear regression with neural network regressionlinear regression · Natural images (Pascal+Caltech+ImageNet)RMSE (%): 8.62 -> 3.04Improved
replace confidence-threshold prediction (tau=0.7) with neural network regressionpredicted score method · Natural images (Pascal+Caltech+ImageNet)RMSE (%): 1.49 -> 3.04Hurt
increase confidence threshold tau from 0.7 to 0.9 (ablation)predicted score method · Natural images (Pascal+Caltech+ImageNet)RMSE (%): 1.49 -> 6.96Hurt
increase confidence threshold tau from 0.7 to 0.9 (ablation)predicted score method · Digits (SVHN+USPS)RMSE (%): 18.11 -> 25.59Hurt
use neural network regression instead of linear regression on Caltechlinear regression · Caltech (12 classes, train COCO)estimated accuracy (%): 79.77 -> 89.39Improved
use neural network regression instead of linear regression on USPSlinear regression · USPS (digits, train MNIST)estimated accuracy (%): 50.14 -> 64.11Improved
increase number of sample sets in the training meta set (ablation)neural network regression · Digits and natural imagesabsolute error (%)Improved
increase number of sample sets in the training meta set (ablation)linear regression · Digits and natural imagesabsolute error (%)No clear effect
increase images per sample set (ablation)neural network regression · Digits and natural imagesabsolute error (%)Improved
increase images per sample set (ablation)linear regression · Digits and natural imagesabsolute error (%)No clear effect

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