Pith. sign in

REVIEW

Geometric Unsupervised Domain Adaptation for Semantic Segmentation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2103.16694 v2 pith:GVG62JL4 submitted 2021-03-30 cs.CV

Geometric Unsupervised Domain Adaptation for Semantic Segmentation

classification cs.CV
keywords domainsemanticadaptationgeometricsegmentationsyntheticunsuperviseddata
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Simulators can efficiently generate large amounts of labeled synthetic data with perfect supervision for hard-to-label tasks like semantic segmentation. However, they introduce a domain gap that severely hurts real-world performance. We propose to use self-supervised monocular depth estimation as a proxy task to bridge this gap and improve sim-to-real unsupervised domain adaptation (UDA). Our Geometric Unsupervised Domain Adaptation method (GUDA) learns a domain-invariant representation via a multi-task objective combining synthetic semantic supervision with real-world geometric constraints on videos. GUDA establishes a new state of the art in UDA for semantic segmentation on three benchmarks, outperforming methods that use domain adversarial learning, self-training, or other self-supervised proxy tasks. Furthermore, we show that our method scales well with the quality and quantity of synthetic data while also improving depth prediction.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.