Attend, Distill, Detect: Attention-aware Entropy Distillation for Anomaly Detection

TL;DR

This paper introduces a novel attention-aware entropy distillation method with a specialized module to improve multi-class anomaly detection, achieving higher accuracy and efficiency in industrial applications.

Contribution

The paper proposes the DCAM module that enhances knowledge distillation by reducing cross-class interference and improving scale-invariance in multi-class anomaly detection.

Findings

Achieved 3.92% performance gain over multi-class baseline.

Effectively reduces irrelevant information during training.

Maintains low latency during inference.

Abstract

Unsupervised anomaly detection encompasses diverse applications in industrial settings where a high-throughput and precision is imperative. Early works were centered around one-class-one-model paradigm, which poses significant challenges in large-scale production environments. Knowledge-distillation based multi-class anomaly detection promises a low latency with a reasonably good performance but with a significant drop as compared to one-class version. We propose a DCAM (Distributed Convolutional Attention Module) which improves the distillation process between teacher and student networks when there is a high variance among multiple classes or objects. Integrated multi-scale feature matching strategy to utilise a mixture of multi-level knowledge from the feature pyramid of the two networks, intuitively helping in detecting anomalies of varying sizes which is also an inherent problem in the multi-class scenario. Briefly, our DCAM module consists of Convolutional Attention blocks distributed across the feature maps of the student network, which essentially learns to masks the irrelevant information during student learning alleviating the "cross-class interference" problem. This process is accompanied by minimizing the relative entropy using KL-Divergence in Spatial dimension and a Channel-wise Cosine Similarity between the same feature maps of teacher and student. The losses enables to achieve scale-invariance and capture non-linear relationships. We also highlight that the DCAM module would only be used during training and not during inference as we only need the learned feature maps and losses for anomaly scoring and hence, gaining a performance gain of 3.92% than the multi-class baseline with a preserved latency.