{"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/classifying-a-specific-image-region-using","title":"Classifying a specific image region using convolutional nets with an ROI mask as input","arxiv_id":"1812.00291","date":"2018-12-01","proceeding":null,"authors":["Sagi Eppel"],"abstract":"Convolutional neural nets (CNN) are the leading computer vision method for\nclassifying images. In some cases, it is desirable to classify only a specific\nregion of the image that corresponds to a certain object. Hence, assuming that\nthe region of the object in the image is known in advance and is given as a\nbinary region of interest (ROI) mask, the goal is to classify the object in\nthis region using a convolutional neural net. This goal is achieved using a\nstandard image classification net with the addition of a side branch, which\nconverts the ROI mask into an attention map. This map is then combined with the\nimage classification net. This allows the net to focus the attention on the\nobject region while still extracting contextual cues from the background. This\napproach was evaluated using the COCO object dataset and the OpenSurfaces\nmaterials dataset. In both cases, it gave superior results to methods that\ncompletely ignore the background region. In addition, it was found that\ncombining the attention map at the first layer of the net gave better results\nthan combining it at higher layers of the net. The advantages of this method\nare most apparent in the classification of small regions which demands a great\ndeal of contextual information from the background.","url_abs":"http://arxiv.org/abs/1812.00291v2","url_pdf":"http://arxiv.org/pdf/1812.00291v2.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":"classifying-a-specific-image-region-using","repo_url":"https://github.com/sagieppel/Classification-of-object-in-a-specific-image-region-using-a-convolutional-neural-net-with-ROI-mask-a","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"classifying-a-specific-image-region-using","repo_url":"https://github.com/sagieppel/Classification-of-the-material-given-region-of-an-image-using-a-convolutional-neural-net-with-attent","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object","task_name":"Object"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}