# Transfer Learning Gaussian Anomaly Detection by Fine-tuning Representations

arXiv: https://arxiv.org/abs/2108.04116 · HTML: https://mlsanity.com/paper/2108.04116/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 73 references that are in the map.
- First posted on arXiv 9 Aug 2021.

## Builds on (most cited first, 30 of 43)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Deep Anomaly Detection with Outlier Exposure](https://mlsanity.com/paper/1812.04606/) (2018)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [PaDiM: a Patch Distribution Modeling Framework for Anomaly Detection and Localization](https://mlsanity.com/paper/2011.08785/) (2020)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [Memorizing Normality to Detect Anomaly: Memory-augmented Deep Autoencoder for Unsupervised Anomaly Detection](https://mlsanity.com/paper/1904.02639/) (2019)
- [Understanding the Effective Receptive Field in Deep Convolutional Neural Networks](https://mlsanity.com/paper/1701.04128/) (2017)
- [CutPaste: Self-Supervised Learning for Anomaly Detection and Localization](https://mlsanity.com/paper/2104.04015/) (2021)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [A Unifying Review of Deep and Shallow Anomaly Detection](https://mlsanity.com/paper/2009.11732/) (2020)
- [GANomaly: Semi-Supervised Anomaly Detection via Adversarial Training](https://mlsanity.com/paper/1805.06725/) (2018)
- [Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddings](https://mlsanity.com/paper/1911.02357/) (2019)
- [Sub-Image Anomaly Detection with Deep Pyramid Correspondences](https://mlsanity.com/paper/2005.02357/) (2020)
- [Deep Anomaly Detection Using Geometric Transformations](https://mlsanity.com/paper/1805.10917/) (2018)
- [Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoders](https://mlsanity.com/paper/1807.02011/) (2018)
- [Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2006.16067/) (2020)
- [Same Same But DifferNet: Semi-Supervised Defect Detection with Normalizing Flows](https://mlsanity.com/paper/2008.12577/) (2020)
- [PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2010.05903/) (2020)
- [Explainable Deep One-Class Classification](https://mlsanity.com/paper/2007.01760/) (2020)

## Built on by (most cited first, 10 of 10)

- [EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies](https://mlsanity.com/paper/2303.14535/) (2023)
- [Deep Industrial Image Anomaly Detection: A Survey](https://mlsanity.com/paper/2301.11514/) (2023)
- [Deep Learning for Unsupervised Anomaly Localization in Industrial Images: A Survey](https://mlsanity.com/paper/2207.10298/) (2022)
- [Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network](https://mlsanity.com/paper/2311.14897/) (2023)
- [Anomaly Detection in 3D Point Clouds using Deep Geometric Descriptors](https://mlsanity.com/paper/2202.11660/) (2022)
- [LafitE: Latent Diffusion Model with Feature Editing for Unsupervised Multi-class Anomaly Detection](https://mlsanity.com/paper/2307.08059/) (2023)
- [Out-of-Distribution Detection Without Class Labels](https://mlsanity.com/paper/2112.07662/) (2021)
- [IPAD: Industrial Process Anomaly Detection Dataset](https://mlsanity.com/paper/2404.15033/) (2024)
- [ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining](https://mlsanity.com/paper/2511.05245/) (2025)
- [Improving Reliability of Fine-tuning with Block-wise Optimisation](https://mlsanity.com/paper/2301.06133/) (2023)

## Abstract (arXiv)

Current state-of-the-art anomaly detection (AD) methods exploit the powerful representations yielded by large-scale ImageNet training. However, catastrophic forgetting prevents the successful fine-tuning of pre-trained representations on new datasets in the semi-supervised setting, and representations are therefore commonly fixed. In our work, we propose a new method to overcome catastrophic forgetting and thus successfully fine-tune pre-trained representations for AD in the transfer learning setting. Specifically, we induce a multivariate Gaussian distribution for the normal class based on the linkage between generative and discriminative modeling, and use the Mahalanobis distance of normal images to the estimated distribution as training objective. We additionally propose to use augmentations commonly employed for vicinal risk minimization in a validation scheme to detect onset of catastrophic forgetting. Extensive evaluations on the public MVTec dataset reveal that a new state of the art is achieved by our method in the AD task while simultaneously achieving anomaly segmentation performance comparable to prior state of the art. Further, ablation studies demonstrate the importance of the induced Gaussian distribution as well as the robustness of the proposed fine-tuning scheme with respect to the choice of augmentations.