Self-Supervised Anomaly Detection by Self-Distillation and Negative Sampling

2022-01-17 · Nima Rafiee, Rahil Gholamipoorfard, Nikolas Adaloglou, Simon Jaxy, Julius Ramakers, Markus Kollmann

Detecting whether examples belong to a given in-distribution or are Out-Of-Distribution (OOD) requires identifying features specific to the in-distribution. In the absence of labels, these features can be learned by self-supervised techniques under the generic assumption that the most abstract features are those which are statistically most over-represented in comparison to other distributions from the same domain. In this work, we show that self-distillation of the in-distribution training set together with contrasting against negative examples derived from shifting transformation of auxiliary data strongly improves OOD detection. We find that this improvement depends on how the negative samples are generated. In particular, we observe that by leveraging negative samples, which keep the statistics of low-level features while changing the high-level semantics, higher average detection performance is obtained. Furthermore, good negative sampling strategies can be identified from the sensitivity of the OOD detection score. The efficiency of our approach is demonstrated across a diverse range of OOD detection problems, setting new benchmarks for unsupervised OOD detection in the visual domain.

📄 PDF Abstract BibTeX arXiv:2201.06378

Code (1)

black0017/black0017 pytorch

Tasks

Anomaly Detection Out of Distribution (OOD) Detection Self-Supervised Anomaly Detection Supervised Anomaly Detection

Anomaly Detection in Video via Self-Supervised and Multi-Task Learning

2020-11-15 · CVPR 2021 1 · Mariana-Iuliana Georgescu, Antonio Barbalau, Radu Tudor Ionescu, Fahad Shahbaz Khan 외

Anomaly detection in video is a challenging computer vision problem. Due to the lack of anomalous events at training time, anomaly detection requires the design of learning methods without full supervision. In this paper…

Abnormal Event Detection In Video Anomaly Detection Anomaly Detection In Surveillance Videos Event Detection+3

jBOT: Semantic Jet Representation Clustering Emerges from Self-Distillation

2026-01-16 · Ho Fung Tsoi, Dylan Rankin arxiv

Self-supervised learning, in the context of foundation model training, is a powerful pre-training method for learning feature representations without labels, which often capture generic underlying semantics from the data…

Self-Supervised Learning Anomaly Detection

Self-Supervised Representation Learning for Visual Anomaly Detection

2020-06-17 · Rabia Ali, Muhammad Umar Karim Khan, Chong Min Kyung

Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, a…

Anomaly Detection General Classification object-detection Object Detection+4

SSMTL++: Revisiting Self-Supervised Multi-Task Learning for Video Anomaly Detection

2022-07-16 · Antonio Barbalau, Radu Tudor Ionescu, Mariana-Iuliana Georgescu, Jacob Dueholm 외

A self-supervised multi-task learning (SSMTL) framework for video anomaly detection was recently introduced in literature. Due to its highly accurate results, the method attracted the attention of many researchers. In th…

Anomaly Detection Knowledge Distillation Multi-Task Learning Optical Flow Estimation+2

Generalist Graph Anomaly Detection via Prototype-Based Distillation

2026-05-26 · Yiming Xu, Zihan Chen, Zhen Peng, Song Wang 외 arxiv

Driven by the pressing demand for graph anomaly detection (GAD) in high-stakes domains, the generalist GAD paradigm, which trains a single detector transferable across new graphs, has recently gained growing attention. H…

Graph Anomaly Detection Graph Neural Network