Multi-Target Domain Transfer Detector on Bad Weather Conditions
- 18 July 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 13, 1-6
Abstract
With the popularization of object detection in fields such as autonomous driving and surveillance, object detection networks are required to be used in more changeable scenarios. However, a multi-target domain adaptive object detection network is a challenging problem. Due to the lack of relevant datasets and the limitation of traditional domain adaptive methods, there is a lack of pertinent research in this field. Traditional single-target domain adaptive methods are often ineffective when used in multi-target domain adaptive problems. To allow the object detection network to be applied to multiple target domains, we propose the “domain transfer module” and the “multi-scale hybrid attention domain alignment module”. At the same time, we synthesized the “BlendedCityspce” dataset for training and testing of a multi-target domain adaptive target object network. The network provided in this paper has a good performance in the multi-target domain adaptation and reaches the state-of-the-art in the single-target domain adaptation. You can find our source code in https://github.com/Chonghuan-Liu/Multi-Target-Domain-Adaptative-Detector.Keywords
Funding Information
- Guangdong Basic and Applied Basic Research Foundation (2021A1515012313)
This publication has 11 references indexed in Scilit:
- Multiscale Domain Adaptive Yolo For Cross-Domain Object Detection2021
- Unsupervised Domain Adaptive Object Detection Using Forward-Backward Cyclic Adaptation2021
- Exploring Categorical Regularization for Domain Adaptive Object Detection2020
- Harmonizing Transferability and Discriminability for Adapting Object Detectors2020
- Progressive Domain Adaptation for Object Detection2020
- Adapting Object Detectors via Selective Cross-Domain Alignment2019
- Strong-Weak Distribution Alignment for Adaptive Object Detection2019
- Domain Adaptive Faster R-CNN for Object Detection in the Wild2018
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- A theory of learning from different domainsMachine Learning, 2009