# RoSAS: Deep Semi-Supervised Anomaly Detection with Contamination-Resilient Continuous Supervision

arXiv: https://arxiv.org/abs/2307.13239 · HTML: https://mlsanity.com/paper/2307.13239/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 50 references that are in the map.
- First posted on arXiv 25 Jul 2023.

## Builds on (most cited first, 26 of 26)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Deep Semi-Supervised Anomaly Detection](https://mlsanity.com/paper/1906.02694/) (2019)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Enhancing Graph Neural Network-based Fraud Detectors against Camouflaged Fraudsters](https://mlsanity.com/paper/2008.08692/) (2020)
- [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)
- [A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data](https://mlsanity.com/paper/1811.08055/) (2018)
- [Deep Learning for Anomaly Detection: A Review](https://mlsanity.com/paper/2007.02500/) (2020)
- [MixUp as Locally Linear Out-Of-Manifold Regularization](https://mlsanity.com/paper/1809.02499/) (2018)
- [Deep Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/1911.08623/) (2019)
- [COPOD: Copula-Based Outlier Detection](https://mlsanity.com/paper/2009.09463/) (2020)
- [Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detection](https://mlsanity.com/paper/2203.14506/) (2022)
- [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)
- [Learning Representations of Ultrahigh-dimensional Data for Random Distance-based Outlier Detection](https://mlsanity.com/paper/1806.04808/) (2018)
- [Explainable Deep Few-shot Anomaly Detection with Deviation Networks](https://mlsanity.com/paper/2108.00462/) (2021)
- [Few-shot Network Anomaly Detection via Cross-network Meta-learning](https://mlsanity.com/paper/2102.11165/) (2021)
- [Deep Weakly-supervised Anomaly Detection](https://mlsanity.com/paper/1910.13601/) (2019)
- [Neural Contextual Anomaly Detection for Time Series](https://mlsanity.com/paper/2107.07702/) (2021)
- [Feature Encoding with AutoEncoders for Weakly-supervised Anomaly Detection](https://mlsanity.com/paper/2105.10500/) (2021)
- [Fascinating Supervisory Signals and Where to Find Them: Deep Anomaly Detection with Scale Learning](https://mlsanity.com/paper/2305.16114/) (2023)
- [Weakly Supervised Anomaly Detection: A Survey](https://mlsanity.com/paper/2302.04549/) (2023)
- [Anomaly Detection by Leveraging Incomplete Anomalous Knowledge with Anomaly-Aware Bidirectional GANs](https://mlsanity.com/paper/2204.13335/) (2022)
- [TiWS-iForest: Isolation Forest in Weakly Supervised and Tiny ML scenarios](https://mlsanity.com/paper/2111.15432/) (2021)

## Built on by (most cited first, 11 of 11)

- [CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection](https://mlsanity.com/paper/2308.09296/) (2023)
- [NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generation](https://mlsanity.com/paper/2311.11961/) (2023)
- [Decomposition-based multi-scale transformer framework for time series anomaly detection](https://mlsanity.com/paper/2504.14206/) (2025)
- [Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor Signals](https://mlsanity.com/paper/2405.06925/) (2024)
- [Outlier detection using flexible categorisation and interrogative agendas](https://mlsanity.com/paper/2312.12010/) (2023)
- [Multi-Normal Prototypes Learning for Weakly Supervised Anomaly Detection](https://mlsanity.com/paper/2408.14498/) (2024)
- [Angel or Devil: Discriminating Hard Samples and Anomaly Contaminations for Unsupervised Time Series Anomaly Detection](https://mlsanity.com/paper/2410.21322/) (2024)
- [Weakly-supervised anomaly detection for multimodal data distributions](https://mlsanity.com/paper/2406.09147/) (2024)
- [Normality Calibration in Semi-supervised Graph Anomaly Detection](https://mlsanity.com/paper/2510.02014/) (2025)
- [IMPACT: Influence Modeling for Open-Set Time Series Anomaly Detection](https://mlsanity.com/paper/2603.29183/) (2026)
- [Rethinking Weak Supervision in Anomaly Detection: A Comprehensive Benchmark](https://mlsanity.com/paper/2605.26068/) (2026)

## Abstract (arXiv)

Semi-supervised anomaly detection methods leverage a few anomaly examples to yield drastically improved performance compared to unsupervised models. However, they still suffer from two limitations: 1) unlabeled anomalies (i.e., anomaly contamination) may mislead the learning process when all the unlabeled data are employed as inliers for model training; 2) only discrete supervision information (such as binary or ordinal data labels) is exploited, which leads to suboptimal learning of anomaly scores that essentially take on a continuous distribution. Therefore, this paper proposes a novel semi-supervised anomaly detection method, which devises textitcontamination-resilient continuous supervisory signals. Specifically, we propose a mass interpolation method to diffuse the abnormality of labeled anomalies, thereby creating new data samples labeled with continuous abnormal degrees. Meanwhile, the contaminated area can be covered by new data samples generated via combinations of data with correct labels. A feature learning-based objective is added to serve as an optimization constraint to regularize the network and further enhance the robustness w.r.t. anomaly contamination. Extensive experiments on 11 real-world datasets show that our approach significantly outperforms state-of-the-art competitors by 20%-30% in AUC-PR and obtains more robust and superior performance in settings with different anomaly contamination levels and varying numbers of labeled anomalies. The source code is available at https://github.com/xuhongzuo/rosas/.