# Self-Tuning Self-Supervised Image Anomaly Detection

arXiv: https://arxiv.org/abs/2306.12033 · HTML: https://mlsanity.com/paper/2306.12033/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 21 Jun 2023.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [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)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [CFLOW-AD: Real-Time Unsupervised Anomaly Detection with Localization via Conditional Normalizing Flows](https://mlsanity.com/paper/2107.12571/) (2021)
- [PairNorm: Tackling Oversmoothing in GNNs](https://mlsanity.com/paper/1909.12223/) (2019)
- [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)
- [Self-supervised Pretraining of Visual Features in the Wild](https://mlsanity.com/paper/2103.01988/) (2021)
- [Fully Convolutional Cross-Scale-Flows for Image-based Defect Detection](https://mlsanity.com/paper/2110.02855/) (2021)
- [Adversarially Learned Anomaly Detection](https://mlsanity.com/paper/1812.02288/) (2018)
- [Modeling the Distribution of Normal Data in Pre-Trained Deep Features for Anomaly Detection](https://mlsanity.com/paper/2005.14140/) (2020)
- [Neural Transformation Learning for Deep Anomaly Detection Beyond Images](https://mlsanity.com/paper/2103.16440/) (2021)
- [OpenDataVal: a Unified Benchmark for Data Valuation](https://mlsanity.com/paper/2306.10577/) (2023)
- [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)

## Built on by (most cited first, 4 of 4)

- [On the Detection of Reviewer-Author Collusion Rings From Paper Bidding](https://mlsanity.com/paper/2402.07860/) (2024)
- [Deep Transductive Outlier Detection](https://mlsanity.com/paper/2404.03495/) (2024)
- [End-To-End Self-Tuning Self-Supervised Time Series Anomaly Detection](https://mlsanity.com/paper/2404.02865/) (2024)
- [Anomaly Detection via Mean Shift Density Enhancement](https://mlsanity.com/paper/2602.03293/) (2026)

## Abstract (arXiv)

Self-supervised learning (SSL) has emerged as a promising paradigm that presents supervisory signals to real-world problems, bypassing the extensive cost of manual labeling. Consequently, self-supervised anomaly detection (SSAD) has seen a recent surge of interest, since SSL is especially attractive for unsupervised tasks. However, recent works have reported that the choice of a data augmentation function has significant impact on the accuracy of SSAD, posing augmentation search as an essential but nontrivial problem due to lack of labeled validation data. In this paper, we introduce ST-SSAD, the first unsupervised approach to end-to-end augmentation tuning for SSAD. To this end, our work presents two key contributions. The first is a new unsupervised validation loss that quantifies the alignment between augmented training data and unlabeled validation data. The second is new differentiable augmentation functions, allowing data augmentation hyperparameter(s) to be tuned in an end-to-end manner. Experiments on two testbeds with semantic class anomalies and subtle industrial defects show that ST-SSAD gives significant performance gains over existing works. All our code and testbeds are available at https://github.com/jaeminyoo/ST-SSAD.