# Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillation

arXiv: https://arxiv.org/abs/2010.05119 · HTML: https://mlsanity.com/paper/2010.05119/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2020.

## Built on by (most cited first, 18 of 18)

- [Dual Memory Units with Uncertainty Regulation for Weakly Supervised Video Anomaly Detection](https://mlsanity.com/paper/2302.05160/) (2023)
- [Segment Any Anomaly without Training via Hybrid Prompt Regularization](https://mlsanity.com/paper/2305.10724/) (2023)
- [Weakly-Supervised Video Anomaly Detection with Snippet Anomalous Attention](https://mlsanity.com/paper/2309.16309/) (2023)
- [On the Fairness of Generative Adversarial Networks (GANs)](https://mlsanity.com/paper/2103.00950/) (2021)
- [Clustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos](https://mlsanity.com/paper/2203.13704/) (2022)
- [Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation](https://mlsanity.com/paper/2306.10534/) (2023)
- [A Novel Data Augmentation Technique for Out-of-Distribution Sample Detection using Compounded Corruptions](https://mlsanity.com/paper/2207.13916/) (2022)
- [Domain Generalization using Ensemble Learning](https://mlsanity.com/paper/2103.10257/) (2021)
- [Adversarial Stacked Auto-Encoders for Fair Representation Learning](https://mlsanity.com/paper/2107.12826/) (2021)
- [Enhancing Zero-Shot Anomaly Detection: CLIP-SAM Collaboration with Cascaded Prompts](https://mlsanity.com/paper/2510.11028/) (2025)
- [Deep Learning Models in Software Requirements Engineering](https://mlsanity.com/paper/2105.07771/) (2021)
- [Not So Robust After All: Evaluating the Robustness of Deep Neural Networks to Unseen Adversarial Attacks](https://mlsanity.com/paper/2308.06467/) (2023)
- [Tabular Data Adapters: Improving Outlier Detection for Unlabeled Private Data](https://mlsanity.com/paper/2504.20862/) (2025)
- [Class-incremental Learning using a Sequence of Partial Implicitly Regularized Classifiers](https://mlsanity.com/paper/2104.01577/) (2021)
- [Analyzing the effectiveness of image augmentations for face recognition from limited data](https://mlsanity.com/paper/2105.08796/) (2021)
- [What augmentations are sensitive to hyper-parameters and why?](https://mlsanity.com/paper/2111.03861/) (2021)
- [Improving Generalizability of Graph Anomaly Detection Models via Data Augmentation](https://mlsanity.com/paper/2209.10168/) (2022)
- [Online Conformal Anomaly Detection with Prediction-Powered Data Acquisition](https://mlsanity.com/paper/2505.01783/) (2025)

## Abstract (arXiv)

Anomaly detection suffers from unbalanced data since anomalies are quite rare. Synthetically generated anomalies are a solution to such ill or not fully defined data. However, synthesis requires an expressive representation to guarantee the quality of the generated data. In this paper, we propose a two-level hierarchical latent space representation that distills inliers' feature-descriptors (through autoencoders) into more robust representations based on a variational family of distributions (through a variational autoencoder) for zero-shot anomaly generation. From the learned latent distributions, we select those that lie on the outskirts of the training data as synthetic-outlier generators. And, we synthesize from them, i.e., generate negative samples without seen them before, to train binary classifiers. We found that the use of the proposed hierarchical structure for feature distillation and fusion creates robust and general representations that allow us to synthesize pseudo outlier samples. And in turn, train robust binary classifiers for true outlier detection (without the need for actual outliers during training). We demonstrate the performance of our proposal on several benchmarks for anomaly detection.