Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors
Not on the map. Why?
Abstract (arXiv)
Anomaly detection methods strive to discover patterns that differ from the norm in a semantic way. This goal is ambiguous as a data point differing from the norm by an attribute e.g., age, race or gender, may be considered anomalous by some operators while others may consider this attribute irrelevant. Breaking from previous research, we present a new anomaly detection method that allows operators to exclude an attribute from being considered as relevant for anomaly detection. Our approach then learns representations which do not contain information over the nuisance attributes. Anomaly scoring is performed using a density-based approach. Importantly, our approach does not require specifying the attributes that are relevant for detecting anomalies, which is typically impossible in anomaly detection, but only attributes to ignore. An empirical investigation is presented verifying the effectiveness of our approach.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 31 of its 40 references that are in the map. First posted on arXiv 7 Jul 2022.
Builds on
31 of 40 references.
References · 31
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
- 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,510
- 2017Billion-scale similarity search with GPUscited by 2,477
- 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
- 2021Towards Total Recall in Industrial Anomaly Detectioncited by 772
- 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
- 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
- 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 331
- 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
19 more
- 2021Contrastive Learning Inverts the Data Generating Processcited by 220
- 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
- 2016What makes ImageNet good for transfer learning?cited by 192
- 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
- 2020Intriguing Properties of Contrastive Lossescited by 129
- 2018Visual Object Networks: Image Generation with Disentangled 3D Representationcited by 124
- 2020DROCC: Deep Robust One-Class Classificationcited by 121
- 2019Domain Agnostic Learning with Disentangled Representationscited by 107
- 2017Multi-Level Variational Autoencoder: Learning Disentangled Representations from Grouped Observationscited by 100
- 2019Are Disentangled Representations Helpful for Abstract Visual Reasoning?cited by 100
- 2017Unsupervised Learning of Disentangled and Interpretable Representations from Sequential Datacited by 92
- 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 87
- 2018Learning Deep Features for One-Class Classificationcited by 76
- 2018Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoderscited by 49
- 2019Demystifying Inter-Class Disentanglementcited by 31
- 2020FairOD: Fairness-aware Outlier Detectioncited by 24
- 2020Towards Fair Deep Anomaly Detectioncited by 24
- 2021Scaling-up Disentanglement for Image Translationcited by 15
- 2022A Contrastive Objective for Learning Disentangled Representationscited by 14
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.