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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add reference images via late fusion under 1% defect training rate (ablation) | ViT · Kaputt (1% defects) | AP any: 57.7 -> 40.4 | Hurt |
| add reference images via late fusion under 1% defect training rate (ablation) | ViT · Kaputt (1% defects) | AUROC: 74.4 -> 63.2 | Hurt |
| use reference images with fine-tuned backbone (AutoGluonMM-ref) versus no references (ablation) | AutoGluonMM · Kaputt | AP any: 87.77 -> 71.21 | Hurt |
| fine-tune PatchCore ResNet50 backbone on training data (ablation) | PatchCore50 · Kaputt | AP any: 35.86 -> 40.18 | Improved |
| reduce defective training samples to 1% defect rate (ablation) | ViT-S · Kaputt | AP any: 90.67 -> 57.7 | Hurt |
| in-context examples for Claude (five defective samples) | Claude · Kaputt | AP any: none -> 36.57 | Improved |
| instruction fine-tune Pixtral with LoRA versus zero-shot (ablation) | Pixtral · Kaputt | AP any: 32.75 -> 33.43 | No clear effect |
| add in-context examples to Pixtral (ablation) | Pixtral · Kaputt | AP any: 32.75 -> 32.18 | No clear effect |
| supervised ViT-S versus best unsupervised baseline | ViT-S · Kaputt | AUROC: 56.96 -> 94.27 | Improved |
Closest papers by meaning
- AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models (AAAI 2024 · similarity 0.89)
- 3CAD: A Large-Scale Real-World 3C Product Dataset for Unsupervised Anomaly Detection (AAAI 2025 · similarity 0.88)
- Supervised Anomaly Detection for Complex Industrial Images (CVPR 2024 · similarity 0.88)
- Real-IAD: A Real-World Multi-View Dataset for Benchmarking Versatile Industrial Anomaly Detection (CVPR 2024 · similarity 0.88)
- Looking 3D: Anomaly Detection with 2D-3D Alignment (CVPR 2024 · similarity 0.87)
- InCLAD: A Continual Learning Benchmark for Industrial Visual Anomaly Detection (NeurIPS 2026 · similarity 0.87)
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.
