Receptive Field Block Net for Accurate and Fast Object Detection

TL;DR

This paper introduces RFB Net, a fast and accurate object detection model that enhances lightweight features with a novel receptive field block inspired by human visual systems, achieving deep detector performance in real-time.

Contribution

The paper proposes a new RF Block (RFB) module that improves feature discriminability and robustness, integrated into SSD to create RFB Net, balancing accuracy and speed.

Findings

RFB Net matches the accuracy of deep detectors.

RFB Net operates in real-time.

Code is publicly available.

Abstract

Current top-performing object detectors depend on deep CNN backbones, such as ResNet-101 and Inception, benefiting from their powerful feature representations but suffering from high computational costs. Conversely, some lightweight model based detectors fulfil real time processing, while their accuracies are often criticized. In this paper, we explore an alternative to build a fast and accurate detector by strengthening lightweight features using a hand-crafted mechanism. Inspired by the structure of Receptive Fields (RFs) in human visual systems, we propose a novel RF Block (RFB) module, which takes the relationship between the size and eccentricity of RFs into account, to enhance the feature discriminability and robustness. We further assemble RFB to the top of SSD, constructing the RFB Net detector. To evaluate its effectiveness, experiments are conducted on two major benchmarks and the results show that RFB Net is able to reach the performance of advanced very deep detectors while keeping the real-time speed. Code is available at https://github.com/ruinmessi/RFBNet.