BiDet: An Efficient Binarized Object Detector

TL;DR

BiDet introduces a binarized neural network approach for object detection that enhances accuracy and reduces false positives by utilizing the information bottleneck principle and sparse priors, outperforming existing binary detectors.

Contribution

The paper presents a novel binarized neural network method for object detection that leverages the information bottleneck principle and sparse priors to improve performance.

Findings

Outperforms state-of-the-art binary neural networks on PASCAL VOC and COCO datasets.

Reduces false positives significantly compared to previous binarized detectors.

Enhances detection precision by fully utilizing the representational capacity of binary networks.

Abstract

In this paper, we propose a binarized neural network learning method called BiDet for efficient object detection. Conventional network binarization methods directly quantize the weights and activations in one-stage or two-stage detectors with constrained representational capacity, so that the information redundancy in the networks causes numerous false positives and degrades the performance significantly. On the contrary, our BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal, through which the detection precision is enhanced with alleviated false positives. Specifically, we generalize the information bottleneck (IB) principle to object detection, where the amount of information in the high-level feature maps is constrained and the mutual information between the feature maps and object detection is maximized. Meanwhile, we learn sparse object priors so that the posteriors are concentrated on informative detection prediction with false positive elimination. Extensive experiments on the PASCAL VOC and COCO datasets show that our method outperforms the state-of-the-art binary neural networks by a sizable margin.