FSSD: Feature Fusion Single Shot Multibox Detector

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.

update info

References in corpus (1)

• DSSD : Deconvolutional Single Shot Detector

Cited by in corpus (22)

• A Survey of Deep Learning-based Object Detection
• Fast object detection in compressed JPEG Images
• GFD-SSD: Gated Fusion Double SSD for Multispectral Pedestrian Detection
• RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devices
• Recent Advances in Deep Learning for Object Detection
• HVNet: Hybrid Voxel Network for LiDAR Based 3D Object Detection
• A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion
• Control Distance IoU and Control Distance IoU Loss Function for Better Bounding Box Regression
• Smart at what cost? Characterising Mobile Deep Neural Networks in the wild
• Detecting retail products in situ using CNN without human effort labeling
• Towards Adversarially Robust Object Detection
• DS-Net++: Dynamic Weight Slicing for Efficient Inference in CNNs and Transformers
• HR-RCNN: Hierarchical Relational Reasoning for Object Detection
• Parsing R-CNN for Instance-Level Human Analysis
• Multispectral Fusion for Object Detection with Cyclic Fuse-and-Refine Blocks
• Small Object Detection Based on Modified FSSD and Model Compression
• ASSD: Attentive Single Shot Multibox Detector
• Localize to Classify and Classify to Localize: Mutual Guidance in Object Detection
• Deep Joint Source-Channel Coding for Multi-Task Network
• FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange
• Detector-in-Detector: Multi-Level Analysis for Human-Parts
• A DCNN-based Arbitrarily-Oriented Object Detector for Quality Control and Inspection Application