CVNov 21, 2017

Receptive Field Block Net for Accurate and Fast Object Detection

arXiv:1711.07767v31512 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the need for fast and accurate object detection in applications like autonomous driving or surveillance, though it is incremental as it builds upon existing SSD architecture.

The authors tackled the trade-off between accuracy and speed in object detection by proposing the RFB Net detector, which integrates a novel RF Block module into SSD to enhance lightweight features, achieving performance comparable to deep detectors while maintaining real-time speed.

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.

Code Implementations8 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes