Improving Novelty Detection using the Reconstructions of Nearest Neighbours
Not on the map. Why?
Abstract (arXiv)
We show that using nearest neighbours in the latent space of autoencoders (AE) significantly improves performance of semi-supervised novelty detection in both single and multi-class contexts. Autoencoding methods detect novelty by learning to differentiate between the non-novel training class(es) and all other unseen classes. Our method harnesses a combination of the reconstructions of the nearest neighbours and the latent-neighbour distances of a given input's latent representation. We demonstrate that our nearest-latent-neighbours (NLN) algorithm is memory and time efficient, does not require significant data augmentation, nor is reliant on pre-trained networks. Furthermore, we show that the NLN-algorithm is easily applicable to multiple datasets without modification. Additionally, the proposed algorithm is agnostic to autoencoder architecture and reconstruction error method. We validate our method across several standard datasets for a variety of different autoencoding architectures such as vanilla, adversarial and variational autoencoders using either reconstruction, residual or feature consistent losses. The results show that the NLN algorithm grants up to a 17% increase in Area Under the Receiver Operating Characteristics (AUROC) curve performance for the multi-class case and 8% for single-class novelty detection.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 58 references that are in the map. First posted on arXiv 11 Nov 2021.
Builds on
34 of 58 references.
References · 34
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2018Deep Anomaly Detection with Outlier Exposurecited by 942
- 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
- 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 531
- 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
- 2018GANomaly: Semi-Supervised Anomaly Detection via Adversarial Trainingcited by 409
- 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
- 2019Uninformed Students: Student-Teacher Anomaly Detection with Discriminative Latent Embeddingscited by 386
- 2015Adversarial Autoencoderscited by 364
- 2019Deep Learning for Anomaly Detection: A Surveycited by 358
22 more
- 2018Improving Unsupervised Defect Segmentation by Applying Structural Similarity to Autoencoderscited by 264
- 2018Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applicationscited by 224
- 2020Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentationcited by 212
- 2018Adversarially Learned One-Class Classifier for Novelty Detectioncited by 202
- 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
- 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
- 2018Latent Space Autoregression for Novelty Detectioncited by 149
- 2018Deep Autoencoding Models for Unsupervised Anomaly Segmentation in Brain MR Imagescited by 146
- 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
- 2018Efficient GAN-Based Anomaly Detectioncited by 122
- 2018Adversarially Learned Anomaly Detectioncited by 115
- 2019Towards Visually Explaining Variational Autoencoderscited by 113
- 2020Deep Nearest Neighbor Anomaly Detectioncited by 104
- 2019Skip-GANomaly: Skip Connected and Adversarially Trained Encoder-Decoder Anomaly Detectioncited by 100
- 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
- 2013One-Class Classification: Taxonomy of Study and Review of Techniquescited by 68
- 2020Generative Adversarial Networks (GANs Survey): Challenges, Solutions, and Future Directionscited by 65
- 2019Detecting semantic anomaliescited by 50
- 2019Deep Transfer Learning for Multiple Class Novelty Detectioncited by 33
- 2019Statistical Analysis of Nearest Neighbor Methods for Anomaly Detectioncited by 29
- 2020Interpretable, Multidimensional, Multimodal Anomaly Detection with Negative Sampling for Detection of Device Failurecited by 27
- 2020Combining GANs and AutoEncoders for Efficient Anomaly Detectioncited by 8
Built on by
Citing papers per year: 2021: 1.
1 paper.