AdvMix: Adversarial Mixing Strategy for Unsupervised Domain Adaptive Object Detection

AdvMix: Adversarial Mixing Strategy for Unsupervised Domain Adaptive Object Detection

Recent object detection networks suffer from performance degradation when training data and test data are distinct in image styles and content distributions. In this paper, we propose a domain adaptive method, Adversarial Mixing (AdvMix), where the label-rich source domain and unlabeled target domai...

Full description

Bibliographic Details
Main Authors: Ruimin Chen, Dailin Lv, Li Dai, Liming Jin, Zhiyu Xiang
Format: Article
Language:English
Published: MDPI AG 2024-02-01
Series:Electronics
Subjects:
object detection
domain adaption
adversarial learning
self-training
Online Access:https://www.mdpi.com/2079-9292/13/4/685

Internet

https://www.mdpi.com/2079-9292/13/4/685

Similar Items