{"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/bilingunet-image-segmentation-by-modulating","title":"Modulating Bottom-Up and Top-Down Visual Processing via Language-Conditional Filters","arxiv_id":"2003.12739","date":"2020-03-28","proceeding":null,"authors":["İlker Kesen","Ozan Arkan Can","Erkut Erdem","Aykut Erdem","Deniz Yuret"],"abstract":"How to best integrate linguistic and perceptual processing in multi-modal tasks that involve language and vision is an important open problem. In this work, we argue that the common practice of using language in a top-down manner, to direct visual attention over high-level visual features, may not be optimal. We hypothesize that the use of language to also condition the bottom-up processing from pixels to high-level features can provide benefits to the overall performance. To support our claim, we propose a U-Net-based model and perform experiments on two language-vision dense-prediction tasks: referring expression segmentation and language-guided image colorization. We compare results where either one or both of the top-down and bottom-up visual branches are conditioned on language. Our experiments reveal that using language to control the filters for bottom-up visual processing in addition to top-down attention leads to better results on both tasks and achieves competitive performance. Our linguistic analysis suggests that bottom-up conditioning improves segmentation of objects especially when input text refers to low-level visual concepts. Code is available at https://github.com/ilkerkesen/bvpr.","url_abs":"https://arxiv.org/abs/2003.12739v3","url_pdf":"https://arxiv.org/pdf/2003.12739v3.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":"bilingunet-image-segmentation-by-modulating","repo_url":"https://github.com/ilkerkesen/bvpr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"colorization","task_name":"Colorization"},{"task_slug":"image-colorization","task_name":"Image Colorization"},{"task_slug":"referring-expression","task_name":"Referring Expression"},{"task_slug":"referring-expression-segmentation","task_name":"Referring Expression Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.12739","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}