CFENet: An Accurate and Efficient Single-Shot Object Detector for Autonomous Driving

TL;DR

CFENet is a novel single-shot object detector that enhances small object detection and maintains high efficiency, achieving competitive accuracy and speed for autonomous driving applications.

Contribution

It introduces the Comprehensive Feature Enhancement (CFE) module into SSD architecture, significantly improving small object detection performance while preserving efficiency.

Findings

Outperforms SSD and RefineDet on small objects

Achieves 21 fps with single-scale input

Reaches 29.69 mAP on MSCOCO dataset

Abstract

The ability to detect small objects and the speed of the object detector are very important for the application of autonomous driving, and in this paper, we propose an effective yet efficient one-stage detector, which gained the second place in the Road Object Detection competition of CVPR2018 workshop - Workshop of Autonomous Driving(WAD). The proposed detector inherits the architecture of SSD and introduces a novel Comprehensive Feature Enhancement(CFE) module into it. Experimental results on this competition dataset as well as the MSCOCO dataset demonstrate that the proposed detector (named CFENet) performs much better than the original SSD and the state-of-the-art method RefineDet especially for small objects, while keeping high efficiency close to the original SSD. Specifically, the single scale version of the proposed detector can run at the speed of 21 fps, while the multi-scale version with larger input size achieves the mAP 29.69, ranking second on the leaderboard