Attend, Distill, Detect: Attention-aware Entropy Distillation for Anomaly Detection
This work addresses the need for high-throughput and precise anomaly detection in industrial settings, offering an incremental improvement over existing multi-class methods.
The paper tackles the problem of performance drop in multi-class anomaly detection using knowledge distillation by proposing a Distributed Convolutional Attention Module (DCAM) that improves distillation between teacher and student networks, achieving a 3.92% performance gain over the baseline while preserving latency.
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.