Low bit‐based convolutional neural network for one‐class object detection

Abstract Low‐performance systems such as mobile and embedded devices require an efficient deep neural network for object detection. In this letter, we propose a very efficient network made by both quantisation and model compression for detecting one class. First, our proposed network uses 1‐bit weights to reduce the kernel parameter size and 8‐bit activations to increase the speed. Second, we optimise the model size and computational power by compressing the maximum number of channels of the network. Therefore, compared to Darknet19, our proposed network infers 35 times faster on the CPU and saves over 7000 times memory. For fair evaluations, we built one‐class object detection databases to detect subtitles of various videos and a specific class from the Pascal VOC database. We verify, compared to Darknet19 and Tiny you only look once (YOLO), that the proposed optimised network does not degrade in object detection accuracy with the efficient and applicable parameter sizes and computational complexity