{"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/robust-scene-change-detection-using-visual","title":"Robust Scene Change Detection Using Visual Foundation Models and Cross-Attention Mechanisms","arxiv_id":"2409.16850","date":"2024-09-25","proceeding":null,"authors":["Chun-Jung Lin","Sourav Garg","Tat-Jun Chin","Feras Dayoub"],"abstract":"We present a novel method for scene change detection that leverages the robust feature extraction capabilities of a visual foundational model, DINOv2, and integrates full-image cross-attention to address key challenges such as varying lighting, seasonal variations, and viewpoint differences. In order to effectively learn correspondences and mis-correspondences between an image pair for the change detection task, we propose to a) ``freeze'' the backbone in order to retain the generality of dense foundation features, and b) employ ``full-image'' cross-attention to better tackle the viewpoint variations between the image pair. We evaluate our approach on two benchmark datasets, VL-CMU-CD and PSCD, along with their viewpoint-varied versions. Our experiments demonstrate significant improvements in F1-score, particularly in scenarios involving geometric changes between image pairs. The results indicate our method's superior generalization capabilities over existing state-of-the-art approaches, showing robustness against photometric and geometric variations as well as better overall generalization when fine-tuned to adapt to new environments. Detailed ablation studies further validate the contributions of each component in our architecture. Source code will be made publicly available upon acceptance.","url_abs":"https://arxiv.org/abs/2409.16850v1","url_pdf":"https://arxiv.org/pdf/2409.16850v1.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":"robust-scene-change-detection-using-visual","repo_url":"https://github.com/ChadLin9596/Robust-Scene-Change-Detection","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"change-detection","task_name":"Change Detection"},{"task_slug":"scene-change-detection","task_name":"Scene Change Detection"}],"methods":[],"datasets_introduced":[{"slug":"unaligned-vl-cmu-cd","name":"Unaligned-VL-CMU-CD (neighbor distance 2)","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-change-detection-on-unaligned-vl-cmu-cd","task":"Scene Change Detection","dataset":"Unaligned-VL-CMU-CD (neighbor distance 2)","model":"Robust-Scene-Change-Detection (Diff-View Augmentation)","rank_in_archive_order":1,"of":2,"metrics":{"F1-score":"0.784"},"uses_additional_data":false},{"leaderboard":"/sota/scene-change-detection-on-unaligned-vl-cmu-cd","task":"Scene Change Detection","dataset":"Unaligned-VL-CMU-CD (neighbor distance 2)","model":"Robust-Scene-Change-Detection","rank_in_archive_order":2,"of":2,"metrics":{"F1-score":"0.739"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2409.16850","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}