Research map / Label-efficient and robust learning / Recognition and long-tail
HRN: A Holistic Approach to One Class Learning
Wenpeng Hu, Mengyu Wang, Qi Qin, Jinwen Ma, Bing Liu
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 H-regularization to NLL loss (ablation) | HRN · MNIST/fMNIST/CIFAR-10 | AUC: 55.42 -> 80.92 (MNIST) | Improved |
| add 2-norm instance normalization (ablation) | NLL+Hreg · CIFAR-10 | AUC: 55.26 -> 71.32 | Improved |
| use 2-norm instance normalization instead of instance normalization of [79] (ablation) | HRN · MNIST | AUC: 92.58 -> 97.59 | Improved |
| replace H-regularization with L2 regularization (ablation) | HRN · MNIST | AUC: 97.59 -> 91.37 | Hurt |
| replace NLL with square loss in full HRN (ablation) | HRN · CIFAR-10 | AUC: 71.32 -> 71.08 | No clear effect |
| square loss instead of NLL without regularization (ablation) | one-class loss · MNIST | AUC: 55.42 -> 76.67 | Improved |
| add 20% noisy training data | HRN · MNIST | AUC: 97.59 -> 92.70 | Hurt |
| add 20% noisy training data | HRN · CIFAR-10 | AUC: 71.32 -> 70.36 | No clear effect |
| ImageNet pre-trained feature extractor | HRN · CIFAR-10 | AUC: 71.27 -> 96.6 | Improved |
| HRN vs TQM baseline | HRN · Thyroid | F1: 75.27 -> 95.87 | Improved |
| HRN vs iForest | HRN · Arrhythmia | F1: 86.43 -> 84.46 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- OCGAN — OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations (CVPR 2019) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Adversarially Learned One-Class Classifier for Novelty Detection (CVPR 2018 · similarity 0.86)
- OCGAN: One-Class Novelty Detection Using GANs With Constrained Latent Representations (CVPR 2019 · similarity 0.86)
- Deep One-Class Classification via Interpolated Gaussian Descriptor (AAAI 2022 · similarity 0.85)
- Learning and Evaluating Representations for Deep One-Class Classification (ICLR 2021 · similarity 0.85)
- ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining (NeurIPS 2025 · similarity 0.83)
- OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning (ICLR 2024 · similarity 0.83)
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.
