Multiscale Domain Adaptive YOLO for Cross-Domain Object Detection
Authors:
Preprint
Abstract
The area of domain adaptation has been instrumental in addressing the domain shift problem encountered by many applications. This problem arises due to the difference between the distributions of source data used for training in comparison with target data used during realistic testing scenarios. In this paper, we introduce a novel MultiScale Domain Adaptive YOLO (MS-DAYOLO) framework that employs multiple domain adaptation paths and corresponding domain classifiers at different scales of the recently introduced YOLOv4 object detector to generate domain-invariant features. We train and test our proposed method using popular datasets. Our experiments show significant improvements in object detection performance when training YOLOv4 using the proposed MS-DAYOLO and when tested on target data representing challenging weather conditions for autonomous driving applications.Keywords
All Related Versions
- Version 1, 2021-06-02, ArXiv
- Version 2, 2022-02-10, ArXiv
- Published version: , 3323.
This publication has 3 references indexed in Scilit:
- Deep Domain Adaptive Object Detection: a Survey2020
- Semantic Foggy Scene Understanding with Synthetic DataInternational Journal of Computer Vision, 2018
- Domain Transfer Multiple Kernel LearningIEEE Transactions on Pattern Analysis and Machine Intelligence, 2012