FSSD: Feature Fusion Single Shot Multibox Detector

TL;DR

FSSD introduces a lightweight feature fusion module to enhance SSD's object detection accuracy by effectively combining multi-scale features, resulting in improved performance with minimal speed reduction.

Contribution

The paper proposes a novel feature fusion module for SSD that significantly boosts detection accuracy while maintaining high speed, addressing the challenge of fusing multi-scale features.

Findings

Achieves 82.7 mAP on Pascal VOC 2007 at 65.8 FPS

Outperforms conventional SSD on COCO dataset

Improves accuracy with minimal speed loss

Abstract

SSD (Single Shot Multibox Detector) is one of the best object detection algorithms with both high accuracy and fast speed. However, SSD's feature pyramid detection method makes it hard to fuse the features from different scales. In this paper, we proposed FSSD (Feature Fusion Single Shot Multibox Detector), an enhanced SSD with a novel and lightweight feature fusion module which can improve the performance significantly over SSD with just a little speed drop. In the feature fusion module, features from different layers with different scales are concatenated together, followed by some down-sampling blocks to generate new feature pyramid, which will be fed to multibox detectors to predict the final detection results. On the Pascal VOC 2007 test, our network can achieve 82.7 mAP (mean average precision) at the speed of 65.8 FPS (frame per second) with the input size 300$\times$300 using a single Nvidia 1080Ti GPU. In addition, our result on COCO is also better than the conventional SSD with a large margin. Our FSSD outperforms a lot of state-of-the-art object detection algorithms in both aspects of accuracy and speed. Code is available at https://github.com/lzx1413/CAFFE_SSD/tree/fssd.