Exploring Categorical Regularization for Domain Adaptive Object Detection

By Xingjie Zhao, Xin Jin, Xiu-Shen Wei. Computer Vision and Pattern Recognition, 2020

341 citations recorded by the source corpus.

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 https://github.com/Megvii-Nanjing/CR-DA-DET.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/ba7de158d110059c9af544d2d282161ca3ee6261

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Cross-Domain Adaptive Teacher for Object Detection (2021, methodology): “We compare our method with SCL [35], SWDA [32], DM [19], CRDA [42], HTCN [2], UMT [8], Source (F-RCNN), and Oracle (F-RCNN).”
Unbiased Mean Teacher for Cross-domain Object Detection (2020, methodology): “However, the improvement is not as significant as other state-of-the-art methods like CRDA, HTCN, and SCL, possibly due to the model bias problem as analyzed in Section 3.3.”