Unified Anomaly Detection methods on Edge Device using Knowledge Distillation and Quantization

TL;DR

This paper explores unified multi-class anomaly detection models for edge devices, demonstrating their efficiency and comparable performance to class-specific models, and evaluates quantization techniques for deployment on resource-constrained hardware.

Contribution

It introduces unified multi-class anomaly detection architectures and compares quantization methods for edge deployment, showing their effectiveness and efficiency.

Findings

Unified models perform on par with one-class models on MVTec AD dataset.

Quantization-aware training maintains performance close to full precision.

Post-training quantization benefits from effective calibration methods.

Abstract

With the rapid advances in deep learning and smart manufacturing in Industry 4.0, there is an imperative for high-throughput, high-performance, and fully integrated visual inspection systems. Most anomaly detection approaches using defect detection datasets, such as MVTec AD, employ one-class models that require fitting separate models for each class. On the contrary, unified models eliminate the need for fitting separate models for each class and significantly reduce cost and memory requirements. Thus, in this work, we experiment with considering a unified multi-class setup. Our experimental study shows that multi-class models perform at par with one-class models for the standard MVTec AD dataset. Hence, this indicates that there may not be a need to learn separate object/class-wise models when the object classes are significantly different from each other, as is the case of the dataset considered. Furthermore, we have deployed three different unified lightweight architectures on the CPU and an edge device (NVIDIA Jetson Xavier NX). We analyze the quantized multi-class anomaly detection models in terms of latency and memory requirements for deployment on the edge device while comparing quantization-aware training (QAT) and post-training quantization (PTQ) for performance at different precision widths. In addition, we explored two different methods of calibration required in post-training scenarios and show that one of them performs notably better, highlighting its importance for unsupervised tasks. Due to quantization, the performance drop in PTQ is further compensated by QAT, which yields at par performance with the original 32-bit Floating point in two of the models considered.