Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection

Anomaly detection has recently gained increasing attention in the field of computer vision, likely due to its broad set of applications ranging from product fault detection on industrial production lines and impending event detection in video surveillance to finding lesions in medical scans. Regardless of the domain, anomaly detection is typically framed as a one-class classification task, where the learning is conducted on normal examples only. An entire family of successful anomaly detection methods is based on learning to reconstruct masked normal inputs (e.g. patches, future frames, etc.) and exerting the magnitude of the reconstruction error as an indicator for the abnormality level. Unlike other reconstruction-based methods, we present a novel self-supervised masked convolutional transformer block (SSMCTB) that comprises the reconstruction-based functionality at a core architectural level. The proposed self-supervised block is extremely flexible, enabling information masking at any layer of a neural network and being compatible with a wide range of neural architectures. In this work, we extend our previous self-supervised predictive convolutional attentive block (SSPCAB) with a 3D masked convolutional layer, a transformer for channel-wise attention, as well as a novel self-supervised objective based on Huber loss. Furthermore, we show that our block is applicable to a wider variety of tasks, adding anomaly detection in medical images and thermal videos to the previously considered tasks based on RGB images and surveillance videos. We exhibit the generality and flexibility of SSMCTB by integrating it into multiple state-of-the-art neural models for anomaly detection, bringing forth empirical results that confirm considerable performance improvements on five benchmarks. We release our code and data as open source at: https://github.com/ristea/ssmctb.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Anomaly Detection CUHK Avenue Background-Agnostic Framework+SSMCTB AUC 93.2% # 4
RBDC 66.04 # 2
TBDC 65.12 # 7
FPS 24 # 7
Anomaly Detection MVTec AD NSA+SSMCTB Detection AUROC 97.7 # 49
Segmentation AUROC 96.7 # 57
Anomaly Detection MVTec AD DRAEM+SSMCTB Detection AUROC 98.7 # 32
Segmentation AUROC 97.2 # 49
Anomaly Detection ShanghaiTech SSMTL+++SSMCTB AUC 83.6% # 8
RBDC 47.73 # 3
TBDC 85.65 # 3

Methods


No methods listed for this paper. Add relevant methods here