# Heterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging Source: [Heterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging]() Collection index: [llms.txt]() Data updated: 2025-10-27T06:55:51.510Z Authors: Jiawen Yang, Shuhao Chen, Yucong Duan, Ke Tang, Yu Zhang Published: 2025-06-19T02:31:51.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()