Name
Abstract | ||
|---|---|---|
Rendering synthetic data (e.g., 3D CAD-rendered images) to generate annotations for learning deep models in vision tasks has attracted increasing attention in recent years. However, simply applying the models learnt on synthetic images may lead to high generalization error on real images due to domain shift. To address this issue, recent progress in cross-domain recognition has featured the Mean Teacher, which directly simulates unsupervised domain adaptation as semi-supervised learning. The domain gap is thus naturally bridged with consistency regularization in a teacher-student scheme. In this work, we advance this Mean Teacher paradigm to be applicable for cross domain detection. Specifically, we present Mean Teacher with Object Relations (MTOR) that novelly remolds Mean Teacher under the backbone of Faster R-CNN by integrating the object relations into the measure of consistency cost between teacher and student modules. Technically, MTOR firstly learns relational graphs that capture similarities between pairs of regions for teacher and student respectively. The whole architecture is then optimized with three consistency regularizations: 1) region-level consistency to align the region-level predictions between teacher and student, 2) inter-graph consistency for matching the graph structures between teacher and student, and 3) intra-graph consistency to enhance the similarity between regions of same class within the graph of student. Extensive experiments are conducted on the transfers across Cityscapes, Foggy Cityscapes, and SIMlOk, and superior results are reported when comparing to state-of-the-art approaches. More remarkably, we obtain a new record of single model: 22.8% of mAP on Syn2Real detection dataset. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/CVPR.2019.01172 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | Volume |
Graph,Architecture,Domain adaptation,Computer science,Object relations theory,Synthetic data,Regularization (mathematics),Artificial intelligence,Real image,Rendering (computer graphics),Machine learning | Journal | abs/1904.11245 |
ISSN | Citations | PageRank |
1063-6919 | 13 | 0.49 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Qi Cai | 1 | 13 | 2.18 |
| Yingwei Pan | 2 | 357 | 23.66 |
| C. W. Ngo | 3 | 4271 | 211.46 |
| Xinmie Tian | 4 | 487 | 38.43 |
| Ling-yu Duan | 5 | 1770 | 124.87 |
| Ting Yao | 6 | 842 | 52.62 |