AI Paper Atlas

Research map / Label-efficient and robust learning / OOD and anomaly detection

Predicting Is Not Understanding: Recognizing and Addressing Underspecification in Machine Learning

Damien Teney, Maxime Peyrard, Ehsan Abbasnejad

ECCV 2022 · Label-efficient and robust learning › OOD and anomaly detection · approach: Out-of-distribution generalization theory · 23 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 independence constraint to ERM (ablation)linear classifier on frozen features · WILDS-Camelyon17 test-OODbest accuracy (%): 68.4 -> 74.6Improved
add on-manifold hard projection (PCA) on top of independence (ablation)linear classifier on frozen features · WILDS-Camelyon17 test-OODbest accuracy (%): 74.6 -> 81.6Improved
add fine-tuning and distillation (ablation)full method · WILDS-Camelyon17 test-OODbest accuracy (%): 81.6 -> 82.5Improved
use PCA instead of VAE for the manifold with hard projection (ablation)Camelyon17 classifier · WILDS-Camelyon17 test-OODbest accuracy (%): 76.3 -> 81.6Improved
add independence constraint to ERM (ablation)MLP ensemble · Collages (average of 4 test sets)accuracy (%): 62.5 -> 63.0No clear effect
add on-manifold constraint to independence loss (PCA, 8 models) (ablation)Collages MLPs · Collages (average of 4 test sets)accuracy (%): 64.2 -> 72.3Improved
use VAE instead of PCA for the manifold (ablation)Collages MLPs · Collages (average of 4 test sets)accuracy (%): 72.3 -> 76.2Improved
add fine-tuning on masked inputs (ablation)Collages proposed method · Collages (average of 4 test sets)accuracy (%): 76.2 -> 84.8Improved
add pairwise combinations (3x) (ablation)Collages proposed method + FT · Collages (average of 4 test sets)accuracy (%): 84.8 -> 85.4Improved
add independence constraint alone on 16 models (ablation)GQA yes/no model · GQA yes/no val (best of N models)accuracy (%): 68.6 -> 68.1No clear effect
add on-manifold constraint to independence on 16 models (ablation)GQA yes/no model · GQA yes/no val (best of N models)accuracy (%): 68.1 -> 69.3Improved
add on-manifold constraint to independence on 16 models (ablation)GQA yes/no model · GQA-OOD Val-tail (best of N models)accuracy (%): 69.6 -> 71.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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