Heterogeneous-Modal Unsupervised Domain Adaptation via Latent Space Bridging
By: Jiawen Yang , Shuhao Chen , Yucong Duan and more
Potential Business Impact:
Lets computers learn from different kinds of pictures.
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.
Similar Papers
Unified modality separation: A vision-language framework for unsupervised domain adaptation
CV and Pattern Recognition
Helps computers learn from pictures and words better.
Bridging the Inter-Domain Gap through Low-Level Features for Cross-Modal Medical Image Segmentation
Image and Video Processing
Helps doctors see inside bodies better.
Balanced Learning for Domain Adaptive Semantic Segmentation
CV and Pattern Recognition
Helps computers better understand pictures of things.