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

by   Mariana-Iuliana Georgescu, et al.

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, we approach anomalous event detection in video through self-supervised and multi-task learning at the object level. We first utilize a pre-trained detector to detect objects. Then, we train a 3D convolutional neural network to produce discriminative anomaly-specific information by jointly learning multiple proxy tasks: three self-supervised and one based on knowledge distillation. The self-supervised tasks are: (i) discrimination of forward/backward moving objects (arrow of time), (ii) discrimination of objects in consecutive/intermittent frames (motion irregularity) and (iii) reconstruction of object-specific appearance information. The knowledge distillation task takes into account both classification and detection information, generating large prediction discrepancies between teacher and student models when anomalies occur. To the best of our knowledge, we are the first to approach anomalous event detection in video as a multi-task learning problem, integrating multiple self-supervised and knowledge distillation proxy tasks in a single architecture. Our lightweight architecture outperforms the state-of-the-art methods on three benchmarks: Avenue, ShanghaiTech and UCSD Ped2. Additionally, we perform an ablation study demonstrating the importance of integrating self-supervised learning and normality-specific distillation in a multi-task learning setting.


page 2

page 7


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

A self-supervised multi-task learning (SSMTL) framework for video anomal...

Fine-grained Anomaly Detection via Multi-task Self-Supervision

Detecting anomalies using deep learning has become a major challenge ove...

Efficient Anomaly Detection Using Self-Supervised Multi-Cue Tasks

Deep anomaly detection has proven to be an efficient and robust approach...

Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection

Anomaly detection has recently gained increasing attention in the field ...

SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation

Feature regression is a simple way to distill large neural network model...

MP-CodeCheck: Evolving Logical Expression Code Anomaly Learning with Iterative Self-Supervision

Machine programming (MP) is concerned with automating software developme...

Discrete neural representations for explainable anomaly detection

The aim of this work is to detect and automatically generate high-level ...