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

Phase Consistent Ecological Domain Adaptation

About

We introduce two criteria to regularize the optimization involved in learning a classifier in a domain where no annotated data are available, leveraging annotated data in a different domain, a problem known as unsupervised domain adaptation. We focus on the task of semantic segmentation, where annotated synthetic data are aplenty, but annotating real data is laborious. The first criterion, inspired by visual psychophysics, is that the map between the two image domains be phase-preserving. This restricts the set of possible learned maps, while enabling enough flexibility to transfer semantic information. The second criterion aims to leverage ecological statistics, or regularities in the scene which are manifest in any image of it, regardless of the characteristics of the illuminant or the imaging sensor. It is implemented using a deep neural network that scores the likelihood of each possible segmentation given a single un-annotated image. Incorporating these two priors in a standard domain adaptation framework improves performance across the board in the most common unsupervised domain adaptation benchmarks for semantic segmentation.

Yanchao Yang, Dong Lao, Ganesh Sundaramoorthi, Stefano Soatto• 2020

Related benchmarks

TaskDatasetResultRank
Semantic segmentationGTA5 → Cityscapes (val)
mIoU44.6
533
Semantic segmentationSYNTHIA to Cityscapes (val)
Rider IoU29.3
435
Semantic segmentationCityscapes 1.0 (val)
mIoU50.5
110
Semantic segmentationGTA5 to Cityscapes 1.0 (val)
Road IoU91
98
Polyp SegmentationKvasir source: CVC target domain
DSC0.736
18
Polyp SegmentationCVC source Kvasir target domain
DSC70.1
18
Showing 6 of 6 rows

Other info

Follow for update