Papers › BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene...

BiMaL: Bijective Maximum Likelihood Approach to Domain Adaptation in Semantic Scene Segmentation

6 Aug 2021ICCV 2021 10arXiv:2108.03267archive 2025-07-28

Thanh-Dat Truong, Chi Nhan Duong, Ngan Le, Son Lam Phung, Chase Rainwater, Khoa Luu

Semantic segmentation aims to predict pixel-level labels. It has become a popular task in various computer vision applications. While fully supervised segmentation methods have achieved high accuracy on large-scale vision datasets, they are unable to generalize on a new test environment or a new domain well. In this work, we first introduce a new Un-aligned Domain Score to measure the efficiency of a learned model on a new target domain in unsupervised manner. Then, we present the new Bijective Maximum Likelihood(BiMaL) loss that is a generalized form of the Adversarial Entropy Minimization without any assumption about pixel independence. We have evaluated the proposed BiMaL on two domains. The proposed BiMaL approach consistently outperforms the SOTA methods on empirical experiments on "SYNTHIA to Cityscapes", "GTA5 to Cityscapes", and "SYNTHIA to Vistas".

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

uark-cviu/bimal officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationScene SegmentationSegmentationSemantic SegmentationUnsupervised Domain Adaptation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Domain Adaptation SYNTHIA-to-Cityscapes BiMaL mIoU 46.2 #23 of 33 Archive leaderboard report
Unsupervised Domain Adaptation GTAV-to-Cityscapes Labels BiMaL mIoU 47.3 #19 of 20 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections