Papers › Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation

Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation

28 Nov 2019CVPR 2020 6arXiv:1911.12796archive 2025-07-28

Shaokai Ye, Kailu Wu, Mu Zhou, Yunfei Yang, Sia Huat Tan, Kaidi Xu, Jiebo Song, Chenglong Bao, Kaisheng Ma

Existing domain adaptation methods aim at learning features that can be generalized among domains. These methods commonly require to update source classifier to adapt to the target domain and do not properly handle the trade off between the source domain and the target domain. In this work, instead of training a classifier to adapt to the target domain, we use a separable component called data calibrator to help the fixed source classifier recover discrimination power in the target domain, while preserving the source domain's performance. When the difference between two domains is small, the source classifier's representation is sufficient to perform well in the target domain and outperforms GAN-based methods in digits. Otherwise, the proposed method can leverage synthetic images generated by GANs to boost performance and achieve state-of-the-art performance in digits datasets and driving scene semantic segmentation. Our method empirically reveals that certain intriguing hints, which can be mitigated by adversarial attack to domain discriminators, are one of the sources for performance degradation under the domain shift.

Paper PDF Conference PDF Code

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

Code

yeshaokai/Calibrator-Domain-Adaptation 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

Adversarial Attack Domain Adaptation Semantic Segmentation Unsupervised Domain Adaptation

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Domain Adaptation	MNIST-to-USPS	CyCleGAN (Light-weight Calibrator)	Accuracy	97.1	#8 of 14	Archive leaderboard	report
Domain Adaptation	SVHN-to-MNIST	CyCleGAN (Light-weight Calibrator)	Accuracy	97.5	#6 of 14	Archive leaderboard	report
Domain Adaptation	USPS-to-MNIST	CyCleGAN (Light-weight Calibrator)	Accuracy	98.3	#4 of 14	Archive leaderboard	report
Synthetic-to-Real Translation	GTAV-to-Cityscapes Labels	Light-weight Calibrator	mIoU	40.5	#66 of 73	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