Research map / Label-efficient and robust learning / OOD and anomaly detection
Density-driven Regularization for Out-of-distribution Detection
Wenjian Huang, Hao Wang, Jiahao Xia, Chengyan Wang, Jianguo Zhang
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 density consistency regularization (DCR) (ablation) | Ours · CIFAR-100 (WideResNet) | mean FPR95%: 77.04 -> 41.59 | Improved |
| add contrastive distribution regularization (CDR) on top of DCR (ablation) | Ours · CIFAR-100 (WideResNet) | mean FPR95%: 41.59 -> 13.35 | Improved |
| add DCR to baseline (ablation) | Ours · CIFAR-100 (WideResNet) | mean AUROC: 80.05 -> 90.84 | Improved |
| add CDR on top of DCR (ablation) | Ours · CIFAR-100 (WideResNet) | mean AUROC: 90.84 -> 96.09 | Improved |
| batch size 256 -> 128 (ablation) | Ours · CIFAR-100 (WideResNet) | mean FPR95%: 13.35 -> 13.43 | No clear effect |
| batch size 256 -> 512 (ablation) | Ours · CIFAR-100 (WideResNet) | mean FPR95%: 13.35 -> 13.63 | No clear effect |
| regularization weight gamma 0.01 -> 0.005 (ablation) | Ours · CIFAR-100 (WideResNet) | mean FPR95%: 13.35 -> 14.08 | Mixed |
| regularization weight gamma 0.01 -> 0.02 (ablation) | Ours · CIFAR-100 (WideResNet) | mean FPR95%: 13.35 -> 12.92 | No clear effect |
| constant r 10 -> 5 (ablation) | Ours · CIFAR-100 (WideResNet) | mean FPR95%: 13.29 -> 14.03 | No clear effect |
| constant r 10 -> 20 (ablation) | Ours · CIFAR-100 (WideResNet) | mean FPR95%: 13.29 -> 12.87 | No clear effect |
| use proposed method instead of Gram on average FPR95% | Ours · CIFAR-100 (ResNet34) | mean FPR95%: 26.51 -> 16.60 | Improved |
| use proposed method instead of Gram on average FPR95% | Ours · CIFAR-100 (WideResNet) | mean FPR95%: 27.66 -> 13.35 | Improved |
Closest papers by meaning
- Learning to Shape In-distribution Feature Space for Out-of-distribution Detection (NeurIPS 2024 · similarity 0.90)
- ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection (ICLR 2024 · similarity 0.89)
- Understanding Likelihood of Normalizing Flow and Image Complexity through the Lens of Out-of-Distribution Detection (AAAI 2024 · similarity 0.89)
- DOS: Diverse Outlier Sampling for Out-of-Distribution Detection (ICLR 2024 · similarity 0.89)
- Exploiting Discrepancy in Feature Statistic for Out-of-Distribution Detection (AAAI 2024 · similarity 0.89)
- Image Background Serves as Good Proxy for Out-of-distribution Data (ICLR 2024 · similarity 0.89)
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.
