{"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/a-fully-convolutional-two-stream-fusion","title":"A Fully Convolutional Two-Stream Fusion Network for Interactive Image Segmentation","arxiv_id":"1807.02480","date":"2018-07-06","proceeding":null,"authors":["Yang Hu","Andrea Soltoggio","Russell Lock","Steve Carter"],"abstract":"In this paper, we propose a novel fully convolutional two-stream fusion\nnetwork (FCTSFN) for interactive image segmentation. The proposed network\nincludes two sub-networks: a two-stream late fusion network (TSLFN) that\npredicts the foreground at a reduced resolution, and a multi-scale refining\nnetwork (MSRN) that refines the foreground at full resolution. The TSLFN\nincludes two distinct deep streams followed by a fusion network. The intuition\nis that, since user interactions are more direct information on\nforeground/background than the image itself, the two-stream structure of the\nTSLFN reduces the number of layers between the pure user interaction features\nand the network output, allowing the user interactions to have a more direct\nimpact on the segmentation result. The MSRN fuses the features from different\nlayers of TSLFN with different scales, in order to seek the local to global\ninformation on the foreground to refine the segmentation result at full\nresolution. We conduct comprehensive experiments on four benchmark datasets.\nThe results show that the proposed network achieves competitive performance\ncompared to current state-of-the-art interactive image segmentation methods","url_abs":"http://arxiv.org/abs/1807.02480v2","url_pdf":"http://arxiv.org/pdf/1807.02480v2.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":"a-fully-convolutional-two-stream-fusion","repo_url":"https://github.com/cyh4/FCTSFN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"caffe2","reach":null}],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"two","task_name":"Vocal Bursts Valence Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}