# Simple and Effective Prevention of Mode Collapse in Deep One-Class Classification

arXiv: https://arxiv.org/abs/2001.08873 · HTML: https://mlsanity.com/paper/2001.08873/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2020.

## Built on by (most cited first, 17 of 17)

- [DASVDD: Deep Autoencoding Support Vector Data Descriptor for Anomaly Detection](https://mlsanity.com/paper/2106.05410/) (2021)
- [Beyond Individual Input for Deep Anomaly Detection on Tabular Data](https://mlsanity.com/paper/2305.15121/) (2023)
- [Deep Contrastive One-Class Time Series Anomaly Detection](https://mlsanity.com/paper/2207.01472/) (2022)
- [What can Discriminator do? Towards Box-free Ownership Verification of Generative Adversarial Network](https://mlsanity.com/paper/2307.15860/) (2023)
- [TracInAD: Measuring Influence for Anomaly Detection](https://mlsanity.com/paper/2205.01362/) (2022)
- [RoCA: Robust Contrastive One-class Time Series Anomaly Detection with Contaminated Data](https://mlsanity.com/paper/2503.18385/) (2025)
- [Deep Random Projection Outlyingness for Unsupervised Anomaly Detection](https://mlsanity.com/paper/2106.15307/) (2021)
- [Near out-of-distribution detection for low-resolution radar micro-Doppler signatures](https://mlsanity.com/paper/2205.07869/) (2022)
- [Self-Supervised Training with Autoencoders for Visual Anomaly Detection](https://mlsanity.com/paper/2206.11723/) (2022)
- [Generalized Reference Kernel for One-class Classification](https://mlsanity.com/paper/2205.00534/) (2022)
- [Flow-based SVDD for anomaly detection](https://mlsanity.com/paper/2108.04907/) (2021)
- [Patch-aware Vector Quantized Codebook Learning for Unsupervised Visual Defect Detection](https://mlsanity.com/paper/2501.09187/) (2025)
- [InForecaster: Forecasting Influenza Hemagglutinin Mutations Through the Lens of Anomaly Detection](https://mlsanity.com/paper/2210.13709/) (2022)
- [Combining Contrastive and Non-Contrastive Losses for Fine-Tuning Pretrained Models in Speech Analysis](https://mlsanity.com/paper/2211.01964/) (2022)
- [Distribution Fitting for Combating Mode Collapse in Generative Adversarial Networks](https://mlsanity.com/paper/2212.01521/) (2022)
- [On Uniformly Scaling Flows: A Density-Aligned Approach to Deep One-Class Classification](https://mlsanity.com/paper/2510.09452/) (2025)
- [Mitigating Convergence Collapse in Fixed-Target Anomaly Detectors via Kernel-Anchored Locality Regularization](https://mlsanity.com/paper/2610.02345/) (2026)

## Abstract (arXiv)

Anomaly detection algorithms find extensive use in various fields. This area of research has recently made great advances thanks to deep learning. A recent method, the deep Support Vector Data Description (deep SVDD), which is inspired by the classic kernel-based Support Vector Data Description (SVDD), is capable of simultaneously learning a feature representation of the data and a data-enclosing hypersphere. The method has shown promising results in both unsupervised and semi-supervised settings. However, deep SVDD suffers from hypersphere collapse -- also known as mode collapse, if the architecture of the model does not comply with certain architectural constraints, e.g. the removal of bias terms. These constraints limit the adaptability of the model and in some cases, may affect the model performance due to learning sub-optimal features. In this work, we consider two regularizers to prevent hypersphere collapse in deep SVDD. The first regularizer is based on injecting random noise via the standard cross-entropy loss. The second regularizer penalizes the minibatch variance when it becomes too small. Moreover, we introduce an adaptive weighting scheme to control the amount of penalization between the SVDD loss and the respective regularizer. Our proposed regularized variants of deep SVDD show encouraging results and outperform a prominent state-of-the-art method on a setup where the anomalies have no apparent geometrical structure.