# Rethinking Assumptions in Deep Anomaly Detection

arXiv: https://arxiv.org/abs/2006.00339 · HTML: https://mlsanity.com/paper/2006.00339/

## Key facts

- Cited by 45 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2020.

## Built on by (most cited first, 30 of 45)

- [Mean-Shifted Contrastive Loss for Anomaly Detection](https://mlsanity.com/paper/2106.03844/) (2021)
- [Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detection](https://mlsanity.com/paper/2207.01463/) (2022)
- [GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection](https://mlsanity.com/paper/2306.12251/) (2023)
- [TFAD: A Decomposition Time Series Anomaly Detection Architecture with Time-Frequency Analysis](https://mlsanity.com/paper/2210.09693/) (2022)
- [Neural Contextual Anomaly Detection for Time Series](https://mlsanity.com/paper/2107.07702/) (2021)
- [Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images](https://mlsanity.com/paper/2205.11474/) (2022)
- [Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection](https://mlsanity.com/paper/2401.15123/) (2024)
- [Data Augmentation is a Hyperparameter: Cherry-picked Self-Supervision for Unsupervised Anomaly Detection is Creating the Illusion of Success](https://mlsanity.com/paper/2208.07734/) (2022)
- [Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations](https://mlsanity.com/paper/2108.04116/) (2021)
- [Towards Accurate Open-Set Recognition via Background-Class Regularization](https://mlsanity.com/paper/2207.10287/) (2022)
- [LARA: A Light and Anti-overfitting Retraining Approach for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2310.05668/) (2023)
- [AI-based Anomaly Detection for Clinical-Grade Histopathological Diagnostics](https://mlsanity.com/paper/2406.14866/) (2024)
- [Understanding the Effect of Bias in Deep Anomaly Detection](https://mlsanity.com/paper/2105.07346/) (2021)
- [INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learning](https://mlsanity.com/paper/2506.03660/) (2025)
- [Anomaly Detection in Echocardiograms with Dynamic Variational Trajectory Models](https://mlsanity.com/paper/2206.15316/) (2022)
- [One-class Damage Detector Using Deeper Fully-Convolutional Data Descriptions for Civil Application](https://mlsanity.com/paper/2303.01732/) (2023)
- [Towards Cross-domain Few-shot Graph Anomaly Detection](https://mlsanity.com/paper/2410.08629/) (2024)
- [Data refinement for fully unsupervised visual inspection using pre-trained networks](https://mlsanity.com/paper/2202.12759/) (2022)
- [Data augmentation and pre-trained networks for extremely low data regimes unsupervised visual inspection](https://mlsanity.com/paper/2106.01277/) (2021)
- [Deep Random Projection Outlyingness for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2106.15307/) (2021)
- [Anomaly Detection in IR Images of PV Modules using Supervised Contrastive Learning](https://mlsanity.com/paper/2112.02922/) (2021)
- [No Shifted Augmentations (NSA): compact distributions for robust self-supervised Anomaly Detection](https://mlsanity.com/paper/2203.10344/) (2022)
- [Semi-supervised anomaly detection algorithm based on KL divergence (SAD-KL)](https://mlsanity.com/paper/2203.14539/) (2022)
- [Set Learning for Accurate and Calibrated Models](https://mlsanity.com/paper/2307.02245/) (2023)
- [Restricted Generative Projection for One-Class Classification and Anomaly Detection](https://mlsanity.com/paper/2307.04097/) (2023)
- [Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor Signals](https://mlsanity.com/paper/2405.06925/) (2024)
- [Semi-supervised Anomaly Detection with Extremely Limited Labels in Dynamic Graphs](https://mlsanity.com/paper/2501.15035/) (2025)
- [ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learning](https://mlsanity.com/paper/2509.23741/) (2025)
- [Anomalous Sound Detection Using a Binary Classification Model and Class Centroids](https://mlsanity.com/paper/2106.06151/) (2021)
- [Out-of-Distribution Detection Using Outlier Detection Methods](https://mlsanity.com/paper/2108.08218/) (2021)

## Abstract (arXiv)

Though anomaly detection (AD) can be viewed as a classification problem (nominal vs. anomalous) it is usually treated in an unsupervised manner since one typically does not have access to, or it is infeasible to utilize, a dataset that sufficiently characterizes what it means to be "anomalous." In this paper we present results demonstrating that this intuition surprisingly seems not to extend to deep AD on images. For a recent AD benchmark on ImageNet, classifiers trained to discern between normal samples and just a few (64) random natural images are able to outperform the current state of the art in deep AD. Experimentally we discover that the multiscale structure of image data makes example anomalies exceptionally informative.