Beyond Deterministic Translation for Unsupervised Domain Adaptation
Eleni Chiou (University College London),* Eleftheria Panagiotaki (University College London), Iasonas Kokkinos (Snap / University College London)
The 33rd British Machine Vision Conference
Abstract
In this work we challenge the common approach of using a one-to-one mapping ('translation') between the source and target domains in unsupervised domain adaptation (UDA). Instead, we rely on stochastic translation to capture inherent translation ambiguities. This allows us to (i) train more accurate target networks by generating multiple outputs conditioned on the same source image, leveraging both accurate translation and data augmentation for appearance variability, (ii) impute robust pseudo-labels for the target data by averaging the predictions of a source network on multiple translated versions of a single target image and (iii) train and ensemble diverse networks in the target domain by modulating the degree of stochasticity in the translations. We report improvements over strong recent baselines, leading to state-of-the-art UDA results on two challenging semantic segmentation benchmarks.Video
Citation
@inproceedings{Chiou_2022_BMVC,
author = {Eleni Chiou and Eleftheria Panagiotaki and Iasonas Kokkinos },
title = {Beyond Deterministic Translation for Unsupervised Domain Adaptation},
booktitle = {33rd British Machine Vision Conference 2022, {BMVC} 2022, London, UK, November 21-24, 2022},
publisher = {{BMVA} Press},
year = {2022},
url = {https://bmvc2022.mpi-inf.mpg.de/0501.pdf}
}
Copyright © 2022
The British Machine Vision Conference is organised by