Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Unsupervised Scene Adaptation with Memory Regularization in vivo

About

We consider the unsupervised scene adaptation problem of learning from both labeled source data and unlabeled target data. Existing methods focus on minoring the inter-domain gap between the source and target domains. However, the intra-domain knowledge and inherent uncertainty learned by the network are under-explored. In this paper, we propose an orthogonal method, called memory regularization in vivo to exploit the intra-domain knowledge and regularize the model training. Specifically, we refer to the segmentation model itself as the memory module, and minor the discrepancy of the two classifiers, i.e., the primary classifier and the auxiliary classifier, to reduce the prediction inconsistency. Without extra parameters, the proposed method is complementary to the most existing domain adaptation methods and could generally improve the performance of existing methods. Albeit simple, we verify the effectiveness of memory regularization on two synthetic-to-real benchmarks: GTA5 -> Cityscapes and SYNTHIA -> Cityscapes, yielding +11.1% and +11.3% mIoU improvement over the baseline model, respectively. Besides, a similar +12.0% mIoU improvement is observed on the cross-city benchmark: Cityscapes -> Oxford RobotCar.

Zhedong Zheng, Yi Yang• 2019

Related benchmarks

TaskDatasetResultRank
Semantic segmentationGTA5 → Cityscapes (val)
mIoU48.3
533
Semantic segmentationSYNTHIA to Cityscapes (val)
Rider IoU25.1
435
Semantic segmentationGTA5 to Cityscapes (test)
mIoU48.3
151
Semantic segmentationSYNTHIA to Cityscapes
Road IoU83.1
150
Semantic segmentationSynthia to Cityscapes (test)
Road IoU82
138
Semantic segmentationCityscapes (val)
mIoU50.3
133
Semantic segmentationCityscapes adaptation from Synthia 1.0 (val)
Person IoU61.3
114
Semantic segmentationGTA5 to Cityscapes 1.0 (val)
Road IoU90.5
98
Semantic segmentationGTA to Cityscapes
Road IoU89.1
72
Semantic segmentationGTA5 to Cityscapes
mIoU48.3
58
Showing 10 of 19 rows

Other info

Follow for update