{"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/learning-at-a-glance-towards-interpretable","title":"Learning at a Glance: Towards Interpretable Data-limited Continual Semantic Segmentation via Semantic-Invariance Modelling","arxiv_id":"2407.15429","date":"2024-07-22","proceeding":null,"authors":["Bo Yuan","Danpei Zhao","Zhenwei Shi"],"abstract":"Continual semantic segmentation (CSS) based on incremental learning (IL) is a great endeavour in developing human-like segmentation models. However, current CSS approaches encounter challenges in the trade-off between preserving old knowledge and learning new ones, where they still need large-scale annotated data for incremental training and lack interpretability. In this paper, we present Learning at a Glance (LAG), an efficient, robust, human-like and interpretable approach for CSS. Specifically, LAG is a simple and model-agnostic architecture, yet it achieves competitive CSS efficiency with limited incremental data. Inspired by human-like recognition patterns, we propose a semantic-invariance modelling approach via semantic features decoupling that simultaneously reconciles solid knowledge inheritance and new-term learning. Concretely, the proposed decoupling manner includes two ways, i.e., channel-wise decoupling and spatial-level neuron-relevant semantic consistency. Our approach preserves semantic-invariant knowledge as solid prototypes to alleviate catastrophic forgetting, while also constraining sample-specific contents through an asymmetric contrastive learning method to enhance model robustness during IL steps. Experimental results in multiple datasets validate the effectiveness of the proposed method. Furthermore, we introduce a novel CSS protocol that better reflects realistic data-limited CSS settings, and LAG achieves superior performance under multiple data-limited conditions.","url_abs":"https://arxiv.org/abs/2407.15429v1","url_pdf":"https://arxiv.org/pdf/2407.15429v1.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":"learning-at-a-glance-towards-interpretable","repo_url":"https://github.com/ybio/lag","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"continual-semantic-segmentation","task_name":"Continual Semantic Segmentation"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"incremental-learning","task_name":"Incremental Learning"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}