Exploring Categorical Regularization for Domain Adaptive Object Detection
Preprint
Abstract
In this paper, we tackle the domain adaptive object detection problem, where the main challenge lies in significant domain gaps between source and target domains. Previous work seeks to plainly align image-level and instance-level shifts to eventually minimize the domain discrepancy. However, they still overlook to match crucial image regions and important instances across domains, which will strongly affect domain shift mitigation. In this work, we propose a simple but effective categorical regularization framework for alleviating this issue. It can be applied as a plug-and-play component on a series of Domain Adaptive Faster R-CNN methods which are prominent for dealing with domain adaptive detection. Specifically, by integrating an image-level multi-label classifier upon the detection backbone, we can obtain the sparse but crucial image regions corresponding to categorical information, thanks to the weakly localization ability of the classification manner. Meanwhile, at the instance level, we leverage the categorical consistency between image-level predictions (by the classifier) and instance-level predictions (by the detection head) as a regularization factor to automatically hunt for the hard aligned instances of target domains. Extensive experiments of various domain shift scenarios show that our method obtains a significant performance gain over original Domain Adaptive Faster R-CNN detectors. Furthermore, qualitative visualization and analyses can demonstrate the ability of our method for attending on the key regions/instances targeting on domain adaptation. Our code is open-source and available at \url{https://github.com/Megvii-Nanjing/CR-DA-DET}.Keywords
All Related Versions
This publication has 20 references indexed in Scilit:
- Deep Learning for Generic Object Detection: A SurveyInternational Journal of Computer Vision, 2019
- Semantic Foggy Scene Understanding with Synthetic DataInternational Journal of Computer Vision, 2018
- Deep Residual Learning for Image Recognition2016
- CNN-RNN: A Unified Framework for Multi-label Image Classification2016
- The Cityscapes Dataset for Semantic Urban Scene Understanding2016
- Learning Deep Features for Discriminative Localization2016
- You Only Look Once: Unified, Real-Time Object Detection2016
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation2014
- Microsoft COCO: Common Objects in Context2014
- The Earth Mover's Distance as a Metric for Image RetrievalInternational Journal of Computer Vision, 2000