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

Domain-Agnostic Prior for Transfer Semantic Segmentation

About

Unsupervised domain adaptation (UDA) is an important topic in the computer vision community. The key difficulty lies in defining a common property between the source and target domains so that the source-domain features can align with the target-domain semantics. In this paper, we present a simple and effective mechanism that regularizes cross-domain representation learning with a domain-agnostic prior (DAP) that constrains the features extracted from source and target domains to align with a domain-agnostic space. In practice, this is easily implemented as an extra loss term that requires a little extra costs. In the standard evaluation protocol of transferring synthesized data to real data, we validate the effectiveness of different types of DAP, especially that borrowed from a text embedding model that shows favorable performance beyond the state-of-the-art UDA approaches in terms of segmentation accuracy. Our research reveals that UDA benefits much from better proxies, possibly from other data modalities.

Xinyue Huo, Lingxi Xie, Hengtong Hu, Wengang Zhou, Houqiang Li, Qi Tian• 2022

Related benchmarks

TaskDatasetResultRank
Semantic segmentationGTA5 → Cityscapes (val)
mIoU59.8
533
Semantic segmentationSYNTHIA to Cityscapes (val)
Rider IoU36.2
435
Semantic segmentationSynthia to Cityscapes (test)
Road IoU84.2
138
Semantic segmentationCityscapes GTA5 source 1.0 (val)
mIoU59.8
49
Showing 4 of 4 rows

Other info

Follow for update