Domain-Adaptive Semantic Segmentation with Memory-Efficient Cross-Domain Transformers


Loading...

Date

2023

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Unsupervised Domain Adaptation (UDA), a process by which a model trained on a well-annotated source dataset is adapted to an unlabeled target dataset, has emerged as a promising solution for deploying semantic segmentation models in scenarios where annotating extensive amounts of data is cost-prohibitive. Although the recent development of UDA strategies exploiting Transformer-based architectures has represented a major advance in the field, current approaches struggle to effectively learn context dependencies in the target domain, leading to suboptimal semantic label predictions. Aiming at addressing this issue, in this work we introduce a generic three-branch Transformer block that combines self- and cross-attention mechanisms for better source and target feature alignment. %in UDA tasks. We then show how the proposed architecture can be seamlessly incorporated into state-of-the-art self-training UDA schemes for semantic segmentation, yielding enhanced adaptation capabilities without increasing the GPU memory footprint during training. The resulting framework significantly outperforms its baseline on benchmarking datasets for synthetic-to-real (+1.4 mIoU on GTA$\rightarrow$Cityscapes and +1.1 mIoU on SYNTHIA$\rightarrow$Cityscapes) and clear-to-adverse-weather (+3.4 mIoU on Cityscapes$\rightarrow$ACDC) UDA. In addition, it achieves superior robustness compared to using existing cross-domain Transformer architectures that require substantially more GPU memory for training.

Publication status

published

Editor

Book title

34th British Machine Vision Conference Proceedings

Journal / series

Volume

Pages / Article No.

837 - 845

Publisher

BMVA Press

Event

34th British Machine Vision Conference (BMVC 2023)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Semantic Scene Understanding; Unsupervised Domain Adaptation

Organisational unit

09559 - Chli, Margarita (ehemalig) / Chli, Margarita (former)

Notes

Poster presentation on October 23, 2023.

Funding

Related publications and datasets

Is part of: