Robust and Computationally-Efficient Anomaly Detection using Powers-of-Two Networks

TL;DR

This paper presents a CNN-based anomaly detection method for videos that enhances robustness and efficiency by using powers-of-two weights and denoising, achieving faster processing and robustness to background motion.

Contribution

The paper introduces a novel approach combining powers-of-two weights and denoising in CNNs, along with GAN-generated motion vectors, to improve anomaly detection robustness and computational efficiency.

Findings

10% faster CNN inference with denoising

Robust detection despite background motion

Effective use of powers-of-two weights for efficiency

Abstract

Robust and computationally efficient anomaly detection in videos is a problem in video surveillance systems. We propose a technique to increase robustness and reduce computational complexity in a Convolutional Neural Network (CNN) based anomaly detector that utilizes the optical flow information of video data. We reduce the complexity of the network by denoising the intermediate layer outputs of the CNN and by using powers-of-two weights, which replaces the computationally expensive multiplication operations with bit-shift operations. Denoising operation during inference forces small valued intermediate layer outputs to zero. The number of zeros in the network significantly increases as a result of denoising, we can implement the CNN about 10% faster than a comparable network while detecting all the anomalies in the testing set. It turns out that denoising operation also provides robustness because the contribution of small intermediate values to the final result is negligible. During training we also generate motion vector images by a Generative Adversarial Network (GAN) to improve the robustness of the overall system. We experimentally observe that the resulting system is robust to background motion.