Research map / Label-efficient and robust learning / OOD and anomaly detection
Triggering Failures: Out-of-Distribution Detection by Learning From Local Adversarial Attacks in Semantic Segmentation
Victor Besnier, Andrei Bursuc, David Picard, Alexandre Briot
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 local adversarial attack training (ablation) | ObsNet · CamVid OOD | fpr95tpr: 54.2 -> 44.6 | Improved |
| add local adversarial attack training (ablation) | ObsNet · StreetHazards | fpr95tpr: 50.1 -> 44.7 | Improved |
| add local adversarial attack training (ablation) | ObsNet · BDD Anomaly | fpr95tpr: 62.4 -> 60.3 | Improved |
| add skip connections (ablation) | ObsNet · CamVid OOD | fpr95tpr: 81.3 -> 54.2 | Improved |
| feed input image to observer (ablation) | ObsNet · CamVid OOD | fpr95tpr: 57.0 -> 54.2 | Improved |
| use SegNet-mimicking architecture instead of small CNN (ablation) | ObsNet · CamVid OOD | fpr95tpr: 60.3 -> 54.2 | Improved |
| add pretraining (ablation) | ObsNet · CamVid OOD | fpr95tpr: 55.7 -> 54.2 | Improved |
| attack random-shape regions instead of all pixels (ablation) | LAA · CamVid OOD | fpr95tpr: 51.9 -> 44.6 | Improved |
| attack random-shape regions instead of sparse pixels (ablation) | LAA · CamVid OOD | fpr95tpr: 54.2 -> 44.6 | Improved |
| adversarial augmentation applied to main segmentation network (ablation) | Bayesian SegNet · CamVid OOD | Mean IoU: 49.6 -> 41.6 | Hurt |
| adversarial augmentation applied to main segmentation network (ablation) | Bayesian SegNet · StreetHazards | Mean IoU: 44.3 -> 37.8 | Hurt |
| replace MC Dropout with ObsNet + LAA (ablation) | OOD detector · CamVid OOD | fpr95tpr: 49.3 -> 44.6 | Improved |
Closest papers by meaning
- Entropy Maximization and Meta Classification for Out-of-Distribution Detection in Semantic Segmentation (ICCV 2021 · similarity 0.89)
- Rethinking Adversary in Semantic Segmentation: An Out-of-Distribution Perspective (ECCV 2026 · similarity 0.89)
- A Likelihood Ratio-Based Approach to Segmenting Unknown Objects (IJCV 2025 · similarity 0.89)
- Splitting & Integrating: Out-of-Distribution Detection via Adversarial Gradient Attribution (ICML 2025 · similarity 0.88)
- Segment Every Out-of-Distribution Object (CVPR 2024 · similarity 0.87)
- RUNA: Object-Level Out-of-Distribution Detection via Regional Uncertainty Alignment of Multimodal Representations (AAAI 2025 · 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.
