{"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/setting-an-attention-region-for-convolutional","title":"Setting an attention region for convolutional neural networks using region selective features, for recognition of materials within glass vessels","arxiv_id":"1708.08711","date":"2017-08-29","proceeding":null,"authors":["Sagi Eppel"],"abstract":"Convolutional neural networks have emerged as the leading method for the\nclassification and segmentation of images. In some cases, it is desirable to\nfocus the attention of the net on a specific region in the image; one such case\nis the recognition of the contents of transparent vessels, where the vessel\nregion in the image is already known. This work presents a valve filter\napproach for focusing the attention of the net on a region of interest (ROI).\nIn this approach, the ROI is inserted into the net as a binary map. The net\nuses a different set of convolution filters for the ROI and background image\nregions, resulting in a different set of features being extracted from each\nregion. More accurately, for each filter used on the image, a corresponding\nvalve filter exists that acts on the ROI map and determines the regions in\nwhich the corresponding image filter will be used. This valve filter\neffectively acts as a valve that inhibits specific features in different image\nregions according to the ROI map. In addition, a new data set for images of\nmaterials in glassware vessels in a chemistry laboratory setting is presented.\nThis data set contains a thousand images with pixel-wise annotation according\nto categories ranging from filled and empty to the exact phase of the material\ninside the vessel. The results of the valve filter approach and fully\nconvolutional neural nets (FCN) with no ROI input are compared based on this\ndata set.","url_abs":"http://arxiv.org/abs/1708.08711v3","url_pdf":"http://arxiv.org/pdf/1708.08711v3.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":"setting-an-attention-region-for-convolutional","repo_url":"https://github.com/sagieppel/Focusing-attention-of-Fully-convolutional-neural-networks-on-Region-of-interest-ROI-input-map-","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"setting-an-attention-region-for-convolutional","repo_url":"https://github.com/sagieppel/Materials-in-Vessels-data-set","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1708.08711","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}