{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/visual-saliency-based-on-multiscale-deep","title":"Visual Saliency Based on Multiscale Deep Features","arxiv_id":"1503.08663","date":"2015-03-30","proceeding":"CVPR 2015 6","authors":["Guanbin Li","Yizhou Yu"],"abstract":"Visual saliency is a fundamental problem in both cognitive and computational\nsciences, including computer vision. In this CVPR 2015 paper, we discover that\na high-quality visual saliency model can be trained with multiscale features\nextracted using a popular deep learning architecture, convolutional neural\nnetworks (CNNs), which have had many successes in visual recognition tasks. For\nlearning such saliency models, we introduce a neural network architecture,\nwhich has fully connected layers on top of CNNs responsible for extracting\nfeatures at three different scales. We then propose a refinement method to\nenhance the spatial coherence of our saliency results. Finally, aggregating\nmultiple saliency maps computed for different levels of image segmentation can\nfurther boost the performance, yielding saliency maps better than those\ngenerated from a single segmentation. To promote further research and\nevaluation of visual saliency models, we also construct a new large database of\n4447 challenging images and their pixelwise saliency annotation. Experimental\nresults demonstrate that our proposed method is capable of achieving\nstate-of-the-art performance on all public benchmarks, improving the F-Measure\nby 5.0% and 13.2% respectively on the MSRA-B dataset and our new dataset\n(HKU-IS), and lowering the mean absolute error by 5.7% and 35.1% respectively\non these two datasets.","url_abs":"http://arxiv.org/abs/1503.08663v3","url_pdf":"http://arxiv.org/pdf/1503.08663v3.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":[],"tasks":[{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"hku-is","name":"HKU-IS","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1503.08663","atlas_url":"https://app.syntology.ai/?focus=1503.08663","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1503.08663"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1503.08663\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1503.08663"},"call":"get_concepts_for_paper(arxiv_id=\"1503.08663\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"300e65f49230a0a47065e335681ed9a6628bd5ead8ada84ebd60649acb909ea2","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}