Paper Info
Title
SC-UDA: Style and Content Gaps aware Unsupervised Domain Adaptation for Object Detection
Abstract
Current state-of-the-art object detectors can have significant performance drop when deployed in the wild due to domain gaps with training data. Unsupervised Domain Adaptation (UDA) is a promising approach to adapt detectors for new domains/environments without any expensive label cost. Previous mainstream UDA works for object detection usually focused on image-level and/or feature-level adaptation by using adversarial learning methods. In this work, we show that such adversarial-based methods can only reduce domain style gap, but cannot address the domain content gap that is also important for object detectors. To overcome this limitation, we propose the SC-UDA framework to concurrently reduce both gaps: We propose fine-grained domain style transfer to reduce the style gaps with finer image details preserved for detecting small objects; Then we leverage the pseudo label-based self-training to reduce content gaps; To address pseudo label error accumulation during self-training, novel optimizations are proposed, including uncertainty-based pseudo labeling and imbalanced mini-batch sampling strategy. Experiment results show that our approach consistently outperforms prior state-of-the-art methods (up to 8.6%, 2.7% and 2.5% mAP on three UDA benchmarks).
Year
DOI
Venue
2022
10.1109/WACV51458.2022.00113
2022 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2022)
DocType
ISSN
Citations 
Conference
2472-6737
0
PageRank 
References 
Authors
0.34
0
10
Name
Order
Citations
PageRank
Fuxun Yu100.68
Di Wang21337143.48
Yinpeng Chen300.34
Nikolaos Karianakis400.34
Tong Shen500.34
Pei Yu600.34
Dimitrios Lymberopoulos700.34
Sidi Lu801.35
Weisong Shi92323163.09
Xiang Chen1011.03