{"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/multi-domain-incremental-learning-for","title":"Multi-Domain Incremental Learning for Semantic Segmentation","arxiv_id":"2110.12205","date":"2021-10-23","proceeding":null,"authors":["Prachi Garg","Rohit Saluja","Vineeth N Balasubramanian","Chetan Arora","Anbumani Subramanian","C. V. Jawahar"],"abstract":"Recent efforts in multi-domain learning for semantic segmentation attempt to learn multiple geographical datasets in a universal, joint model. A simple fine-tuning experiment performed sequentially on three popular road scene segmentation datasets demonstrates that existing segmentation frameworks fail at incrementally learning on a series of visually disparate geographical domains. When learning a new domain, the model catastrophically forgets previously learned knowledge. In this work, we pose the problem of multi-domain incremental learning for semantic segmentation. Given a model trained on a particular geographical domain, the goal is to (i) incrementally learn a new geographical domain, (ii) while retaining performance on the old domain, (iii) given that the previous domain's dataset is not accessible. We propose a dynamic architecture that assigns universally shared, domain-invariant parameters to capture homogeneous semantic features present in all domains, while dedicated domain-specific parameters learn the statistics of each domain. Our novel optimization strategy helps achieve a good balance between retention of old knowledge (stability) and acquiring new knowledge (plasticity). We demonstrate the effectiveness of our proposed solution on domain incremental settings pertaining to real-world driving scenes from roads of Germany (Cityscapes), the United States (BDD100k), and India (IDD).","url_abs":"https://arxiv.org/abs/2110.12205v1","url_pdf":"https://arxiv.org/pdf/2110.12205v1.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":"multi-domain-incremental-learning-for","repo_url":"https://github.com/prachigarg23/mdil-ss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"scene-segmentation","task_name":"Scene Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.12205","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}