AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Kaputt: A Large-Scale Dataset for Visual Defect Detection

Sebastian Höfer, Dorian F. Henning, Artemij Amiranashvili, Douglas Morrison, Mariliza Tzes, Ingmar Posner, Marc Matvienko, Alessandro Rennola, Anton Milan

ICCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 4 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 reference images via late fusion under 1% defect training rate (ablation)ViT · Kaputt (1% defects)AP any: 57.7 -> 40.4Hurt
add reference images via late fusion under 1% defect training rate (ablation)ViT · Kaputt (1% defects)AUROC: 74.4 -> 63.2Hurt
use reference images with fine-tuned backbone (AutoGluonMM-ref) versus no references (ablation)AutoGluonMM · KaputtAP any: 87.77 -> 71.21Hurt
fine-tune PatchCore ResNet50 backbone on training data (ablation)PatchCore50 · KaputtAP any: 35.86 -> 40.18Improved
reduce defective training samples to 1% defect rate (ablation)ViT-S · KaputtAP any: 90.67 -> 57.7Hurt
in-context examples for Claude (five defective samples)Claude · KaputtAP any: none -> 36.57Improved
instruction fine-tune Pixtral with LoRA versus zero-shot (ablation)Pixtral · KaputtAP any: 32.75 -> 33.43No clear effect
add in-context examples to Pixtral (ablation)Pixtral · KaputtAP any: 32.75 -> 32.18No clear effect
supervised ViT-S versus best unsupervised baselineViT-S · KaputtAUROC: 56.96 -> 94.27Improved

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