# Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning

arXiv: https://arxiv.org/abs/2305.16114 · HTML: https://mlsanity.com/paper/2305.16114/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 39 references that are in the map.
- First posted on arXiv 25 May 2023.

## Builds on (most cited first, 21 of 21)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances](https://mlsanity.com/paper/2007.08176/) (2020)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [SSD: A Unified Framework for Self-Supervised Outlier Detection](https://mlsanity.com/paper/2103.12051/) (2021)
- [ADBench: Anomaly Detection Benchmark](https://mlsanity.com/paper/2206.09426/) (2022)
- [PyOD: A Python Toolbox for Scalable Outlier Detection](https://mlsanity.com/paper/1901.01588/) (2019)
- [Classification-Based Anomaly Detection for General Data](https://mlsanity.com/paper/2005.02359/) (2020)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [Deep Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/1911.08623/) (2019)
- [Explainable Deep One-Class Classification](https://mlsanity.com/paper/2007.01760/) (2020)
- [DROCC: Deep Robust One-Class Classification](https://mlsanity.com/paper/2002.12718/) (2020)
- [Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection](https://mlsanity.com/paper/2111.09099/) (2021)
- [Neural Transformation Learning for Deep Anomaly Detection Beyond Images](https://mlsanity.com/paper/2103.16440/) (2021)
- [Deep Isolation Forest for Anomaly Detection](https://mlsanity.com/paper/2206.06602/) (2022)
- [Self-trained Deep Ordinal Regression for End-to-End Video Anomaly Detection](https://mlsanity.com/paper/2003.06780/) (2020)
- [Generative Adversarial Active Learning for Unsupervised Outlier Detection](https://mlsanity.com/paper/1809.10816/) (2018)
- [Latent Outlier Exposure for Anomaly Detection with Contaminated Data](https://mlsanity.com/paper/2202.08088/) (2022)

## Built on by (most cited first, 25 of 25)

- [RoSAS: Deep Semi-Supervised Anomaly Detection with Contamination-Resilient Continuous Supervision](https://mlsanity.com/paper/2307.13239/) (2023)
- [Disentangling Tabular Data Towards Better One-Class Anomaly Detection](https://mlsanity.com/paper/2411.07574/) (2024)
- [ICLAD: In-Context Learning for Unified Tabular Anomaly Detection Across Supervision Regimes](https://mlsanity.com/paper/2603.19497/) (2026)
- [Domain Adaptive and Fine-grained Anomaly Detection for Single-cell Sequencing Data and Beyond](https://mlsanity.com/paper/2404.17454/) (2024)
- [ReTabAD: A Benchmark for Restoring Semantic Context in Tabular Anomaly Detection](https://mlsanity.com/paper/2510.02060/) (2025)
- [Unsupervised Outlier Detection using Random Subspace and Subsampling Ensembles of Dirichlet Process Mixtures](https://mlsanity.com/paper/2401.00773/) (2024)
- [STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment](https://mlsanity.com/paper/2509.06693/) (2025)
- [Outlier detection using flexible categorisation and interrogative agendas](https://mlsanity.com/paper/2312.12010/) (2023)
- [Flexible categorization using formal concept analysis and Dempster-Shafer theory](https://mlsanity.com/paper/2408.15012/) (2024)
- [Contextual Learning for Anomaly Detection in Tabular Data](https://mlsanity.com/paper/2509.09030/) (2025)
- [CausalTAD: Injecting Causal Knowledge into Large Language Models for Tabular Anomaly Detection](https://mlsanity.com/paper/2602.07798/) (2026)
- [Diffuse to Detect: Generative Diffusion Models for Unsupervised IC Anomaly Detection](https://mlsanity.com/paper/2605.26468/) (2026)
- [Rethinking Unsupervised Outlier Detection via Multiple Thresholding](https://mlsanity.com/paper/2407.05382/) (2024)
- [A Radon-Nikod'ym Perspective on Anomaly Detection: Theory and Implications](https://mlsanity.com/paper/2502.18002/) (2025)
- [UniOD: A Universal Model for Outlier Detection across Diverse Domains](https://mlsanity.com/paper/2507.06624/) (2025)
- [SARD: Segmentation-Aware Anomaly Synthesis via Region-Constrained Diffusion with Discriminative Mask Guidance](https://mlsanity.com/paper/2508.03143/) (2025)
- [Mitigating Long-Tailed Anomaly Score Distributions with Importance-Weighted Loss](https://mlsanity.com/paper/2601.02440/) (2026)
- [Stochastic Voronoi Ensembles for Anomaly Detection](https://mlsanity.com/paper/2601.03664/) (2026)
- [Exploring Multimodal Prompts For Unsupervised Continuous Anomaly Detection](https://mlsanity.com/paper/2603.21562/) (2026)
- [Kurtosis-Guided Denoising Score Matching for Tabular Anomaly Detection](https://mlsanity.com/paper/2605.06955/) (2026)
- [When Normality Shifts: Risk-Aware Test-Time Adaptation for Unsupervised Tabular Anomaly Detection](https://mlsanity.com/paper/2605.10242/) (2026)
- [RGLD: Randomized Global-Local Density Estimation for Tabular Anomaly Detection](https://mlsanity.com/paper/2606.28970/) (2026)
- [Robust Zero-shot Anomaly Detection under Limited Auxiliary Anomaly Priors](https://mlsanity.com/paper/2606.29428/) (2026)
- [LLM as Detector: An In-context Learning Approach for Tabular Anomaly Detection](https://mlsanity.com/paper/2608.19463/) (2026)
- [Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical Data](https://mlsanity.com/paper/2609.03878/) (2026)

## Abstract (arXiv)

Due to the unsupervised nature of anomaly detection, the key to fueling deep models is finding supervisory signals. Different from current reconstruction-guided generative models and transformation-based contrastive models, we devise novel data-driven supervision for tabular data by introducing a characteristic -- scale -- as data labels. By representing varied sub-vectors of data instances, we define scale as the relationship between the dimensionality of original sub-vectors and that of representations. Scales serve as labels attached to transformed representations, thus offering ample labeled data for neural network training. This paper further proposes a scale learning-based anomaly detection method. Supervised by the learning objective of scale distribution alignment, our approach learns the ranking of representations converted from varied subspaces of each data instance. Through this proxy task, our approach models inherent regularities and patterns within data, which well describes data "normality". Abnormal degrees of testing instances are obtained by measuring whether they fit these learned patterns. Extensive experiments show that our approach leads to significant improvement over state-of-the-art generative/contrastive anomaly detection methods.