{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fusion-then-distillation-toward-cross-modal","title":"Fusion-then-Distillation: Toward Cross-modal Positive Distillation for Domain Adaptive 3D Semantic Segmentation","arxiv_id":"2410.19446","date":"2024-10-25","proceeding":null,"authors":["Yao Wu","Mingwei Xing","Yachao Zhang","Yuan Xie","Yanyun Qu"],"abstract":"In cross-modal unsupervised domain adaptation, a model trained on source-domain data (e.g., synthetic) is adapted to target-domain data (e.g., real-world) without access to target annotation. Previous methods seek to mutually mimic cross-modal outputs in each domain, which enforces a class probability distribution that is agreeable in different domains. However, they overlook the complementarity brought by the heterogeneous fusion in cross-modal learning. In light of this, we propose a novel fusion-then-distillation (FtD++) method to explore cross-modal positive distillation of the source and target domains for 3D semantic segmentation. FtD++ realizes distribution consistency between outputs not only for 2D images and 3D point clouds but also for source-domain and augment-domain. Specially, our method contains three key ingredients. First, we present a model-agnostic feature fusion module to generate the cross-modal fusion representation for establishing a latent space. In this space, two modalities are enforced maximum correlation and complementarity. Second, the proposed cross-modal positive distillation preserves the complete information of multi-modal input and combines the semantic content of the source domain with the style of the target domain, thereby achieving domain-modality alignment. Finally, cross-modal debiased pseudo-labeling is devised to model the uncertainty of pseudo-labels via a self-training manner. Extensive experiments report state-of-the-art results on several domain adaptive scenarios under unsupervised and semi-supervised settings. Code is available at https://github.com/Barcaaaa/FtD-PlusPlus.","url_abs":"https://arxiv.org/abs/2410.19446v1","url_pdf":"https://arxiv.org/pdf/2410.19446v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fusion-then-distillation-toward-cross-modal","repo_url":"https://github.com/barcaaaa/ftd-plusplus","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.19446","atlas_url":"https://app.syntology.ai/?focus=2410.19446","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}