{"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/shallow-and-deep-convolutional-networks-for","title":"Shallow and Deep Convolutional Networks for Saliency Prediction","arxiv_id":"1603.00845","date":"2016-03-02","proceeding":"CVPR 2016 6","authors":["Junting Pan","Kevin McGuinness","Elisa Sayrol","Noel O'Connor","Xavier Giro-i-Nieto"],"abstract":"The prediction of salient areas in images has been traditionally addressed\nwith hand-crafted features based on neuroscience principles. This paper,\nhowever, addresses the problem with a completely data-driven approach by\ntraining a convolutional neural network (convnet). The learning process is\nformulated as a minimization of a loss function that measures the Euclidean\ndistance of the predicted saliency map with the provided ground truth. The\nrecent publication of large datasets of saliency prediction has provided enough\ndata to train end-to-end architectures that are both fast and accurate. Two\ndesigns are proposed: a shallow convnet trained from scratch, and a another\ndeeper solution whose first three layers are adapted from another network\ntrained for classification. To the authors knowledge, these are the first\nend-to-end CNNs trained and tested for the purpose of saliency prediction.","url_abs":"http://arxiv.org/abs/1603.00845v1","url_pdf":"http://arxiv.org/pdf/1603.00845v1.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":"shallow-and-deep-convolutional-networks-for","repo_url":"https://github.com/imatge-upc/saliency-2016-cvpr","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"saliency-prediction","task_name":"Saliency Prediction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1603.00845","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}