• Home
  • Search
  • Unsupervised Domain Adaptation for Object Detection Using Distribution Matching in Various Feature Level
  • Cite Icon2
  • https://doi.org/10.1007/978-3-030-11389-6_27Copy DOI Icon

Unsupervised Domain Adaptation for Object Detection Using Distribution Matching in Various Feature Level

  • Jan 1, 2019
  • Hyoungwoo Park +3 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

As the research on deep learning has become more active, the need for a lot of data has emerged. However, there are limitations in acquiring real data such as digital forensics, so domain adaptation technology is required to overcome this problem. This paper considers distribution matching in various feature level for unsupervised domain adaptation for object detection with a single stage detector. The object detection task assumes that training and test data are drawn from the same distribution; however, in a real environment, there is a domain gap between training and test data which leads to degrading performance significantly. Therefore, we aim to learn a model to generalize well in target domain of object detection by using maximum mean discrepancy (MMD) in various feature levels. We adjust MMD based on single shot multibox detector (SSD) model which is a single stage detector that learns to localize objects with various size using a multi-layer design of bounding box regression and infers object class simultaneously. The MMD loss on high-level features between source and target domain effectively reduces the domain discrepancy to learn a domain-invariant feature in SSD model. We evaluate the approaches using Syn2real object detection dataset. Experimental results show that reducing the domain shift in high-level features improves the cross-domain robustness of object detection, and domain adaptation works better with simple MMD method than complex method as GAN.

Similar Papers
  • Research Article
  • Citations67

A novel deep learning‐based single shot multibox detector model for object detection in optical remote sensing images

  • May 16, 2022
  • Geoscience Data Journal
  • Liguo Wang +7
  • Conference Article
  • Citations1

An automatic segmentation method of left myocardium based on SSD model and CNN

  • Nov 01, 2017
  • Shengjie Wu +3
  • Research Article
  • Citations24

Research on Spatial Positioning System of Fruits to be Picked in Field Based on Binocular Vision and SSD Model

  • Jan 01, 2021
  • Journal of Physics: Conference Series
  • Xing Zhang +4
  • Research Article
  • Citations17

A robust object detection system with occlusion handling for mobile devices

  • Feb 20, 2022
  • Computational Intelligence
  • Devi M Chilukuri +2
  • PDF
  • Research Article
  • Citations8

Large-Truck Safety Warning System Based on Lightweight SSD Model.

  • Oct 13, 2019
  • Computational intelligence and neuroscience
  • Dong Xiao +3
  • Research Article
  • Citations4

Sewing gesture image detection method based on improved SSD model

  • Mar 15, 2021
  • Electronics Letters
  • Wenjie Wang +3
  • Book Chapter
  • Citations5

Pedestrian Detection Method Based on SSD Model

  • Jan 01, 2019
  • Xin Li +2
  • Research Article
  • Citations9

Detection of cabinet in equipment floor based on AlexNet and SSD model

  • Feb 20, 2019
  • The Journal of Engineering
  • Lin Lv +1
  • Book Chapter
  • Citations15

Improved SSD-Based Multi-scale Pedestrian Detection Algorithm

  • Jan 01, 2020
  • Di Fan +4
  • Research Article
  • Citations5

AlertTrap: A Study on Object Detection in Remote Insect Trap Monitoring System Using on the Edge Deep Learning Platform

  • Jun 24, 2024
  • Journal of Computational and Cognitive Engineering
  • An Le +3
  • Book Chapter
  • Citations4

An Improved SSD and Its Application in Train Bolt Detection

  • Jan 01, 2020
  • Jiabing Zhang +2
  • Book Chapter
  • Citations16

Deep Learning Based Vehicle Make-Model Classification

  • Jan 01, 2018
  • Burak Satar +1
  • Research Article
  • Citations108

Combining a single shot multibox detector with transfer learning for ship detection using sentinel-1 SAR images

  • May 28, 2018
  • Remote Sensing Letters
  • Yuanyuan Wang +2
  • Addendum
  • Citations17

WITHDRAWN: People detection and counting using YOLOv3 and SSD models

  • Jan 01, 2021
  • Materials Today: Proceedings
  • Pooja Gupta +2
  • Research Article
  • Citations6

Classification and recognition of the Nantong blue calico pattern based on deep learning

  • Jan 01, 2024
  • Journal of Engineered Fibers and Fabrics
  • Ke-Ke Sun +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.