Particle Swarm Loss for Lightweight Object Detection

Currently in object detection, deep learning based detectors are gaining their momentum. However, the supervision involved in the widely-used anchor paradigm within the detection pipeline is inadequate. Traditional object detectors opt for densely picking anchors to increase the training samples for...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhang, Peizhen, Zheng, Feng, Du, Junlong, Zhang, Jun, Guo, Xiaowei, Zheng, Wei-Shi
Format: Conference Proceeding
Language:English
Subjects:
Convolution
deep learning
detection
Detectors
lightweight
Object detection
Particle swarm optimization
Task analysis
Training
Visualization
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Currently in object detection, deep learning based detectors are gaining their momentum. However, the supervision involved in the widely-used anchor paradigm within the detection pipeline is inadequate. Traditional object detectors opt for densely picking anchors to increase the training samples for faster convergence and better detection quality. However, dense anchor scheme requires extra computational budget which renders it infeasible for lightweight detectors. To address the problem, inspired by the cognitive consistency, we propose a novel Particle Swarm Loss for lightweight object detection. Experiments upon the MS-COCO challenge show that detectors compensated by PS loss can not only converge faster but also acquire better detection quality than their vanilla versions (YOLOv3 and SSD improves 2.0% and 2.5% on the harsh AP50 respectively) without extra computational overhead. In addition, we propose a dapper backbone with high cost-efficiency for the resource-limited scenarios.
ISSN:1945-788X
DOI:10.1109/ICME.2019.00029