AI Paper Atlas

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

Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet

Yannic Neuhaus, Maximilian Augustin, Valentyn Boreiko, Matthias Hein

ICCV 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 30 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
apply SpuFix (project out spurious feature directions) to robust ResNet50Robust ResNet50 · Spurious ImageNetmAUC: 0.630 -> 0.763Improved
apply SpuFix to robust ResNet50Robust ResNet50 · ImageNet valaccuracy: 57.4% -> 56.8%Hurt
transfer SpuFix to VOLO-D5 trained on ImageNet1kVOLO-D5 512 · Spurious ImageNetmAUC: 0.882 -> 0.907Improved
transfer SpuFix to models fine-tuned from ImageNet21k or trained on large dataBEiT-L/16, EVA-G/14 CLIP · Spurious ImageNetmAUC: 0.921 -> 0.927 (BEiT-L)Improved
pre-train on ImageNet21k then fine-tune on 1kViT-B AugReg · Spurious ImageNetmAUC: 0.850 -> 0.917Improved
train on larger datasets (JFT, Instagram, LAION, MIM, CLIP)ImageNet classifiers · Spurious ImageNetmAUCNo clear effect
fine-tune ImageNet21k ViT-B on ImageNet1kViT-B AugReg · Spurious ImageNetmAUC: 0.931 -> 0.917No 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