Heterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging

ICLR 2026 Conference Submission13127 Authors

Keywords: Transfer learning, Domain adaptation, Heterogeneous-modal unsupervised domain adaptation

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.

Primary Area: transfer learning, meta learning, and lifelong learning

Submission Number: 13127