Papers › Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised...

Exploiting Image Translations via Ensemble Self-Supervised Learning for Unsupervised Domain Adaptation

13 Jul 2021arXiv:2107.06235archive 2025-07-28

Fabrizio J. Piva, Gijs Dubbelman

We introduce an unsupervised domain adaption (UDA) strategy that combines multiple image translations, ensemble learning and self-supervised learning in one coherent approach. We focus on one of the standard tasks of UDA in which a semantic segmentation model is trained on labeled synthetic data together with unlabeled real-world data, aiming to perform well on the latter. To exploit the advantage of using multiple image translations, we propose an ensemble learning approach, where three classifiers calculate their prediction by taking as input features of different image translations, making each classifier learn independently, with the purpose of combining their outputs by sparse Multinomial Logistic Regression. This regression layer known as meta-learner helps to reduce the bias during pseudo label generation when performing self-supervised learning and improves the generalizability of the model by taking into consideration the contribution of each classifier. We evaluate our method on the standard UDA benchmarks, i.e. adapting GTA V and Synthia to Cityscapes, and achieve state-of-the-art results in the mean intersection over union metric. Extensive ablation experiments are reported to highlight the advantageous properties of our proposed UDA strategy.

Paper PDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Domain Adaptation Domain Generalization Ensemble Learning Image-to-Image Translation Pseudo Label Self-Supervised Learning Semantic Segmentation Synthetic-to-Real Translation Unsupervised Domain Adaptation regression

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Domain Generalization	WildDash	ITEN	Mean IoU	31.2	#1 of 1	Archive leaderboard	report
Synthetic-to-Real Translation	GTAV-to-Cityscapes Labels	ITEN	mIoU	51.66	#40 of 73	Archive leaderboard	report
Synthetic-to-Real Translation	SYNTHIA-to-Cityscapes	ITEN	MIoU (16 classes)	46.45	#28 of 38	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.

Methods

Logistic Regression

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