Unsupervised domain adaptation (UDA) methods effectively bridge domain gaps but become struggled when the source and target domains belong to entirely distinct modalities. To address this limitation, we propose a novel setting called Heterogeneous-Modal Unsupervised Domain Adaptation (HMUDA), which enables knowledge transfer between completely different modalities by leveraging a bridge domain containing unlabeled samples from both modalities. To learn under the HMUDA setting, we propose Latent Space Bridging (LSB), a specialized framework designed for the semantic segmentation task. Specifically, LSB utilizes a dual-branch architecture, incorporating a feature consistency loss to align representations across modalities and a domain alignment loss to reduce discrepancies between class centroids across domains. Extensive experiments conducted on six benchmark datasets demonstrate that LSB achieves state-of-the-art performance.
@article{arxiv.2506.15971,
title = {Heterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging},
author = {Jiawen Yang and Shuhao Chen and Yucong Duan and Ke Tang and Yu Zhang},
journal= {arXiv preprint arXiv:2506.15971},
year = {2025}
}