{"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/multiclass-weighted-loss-for-instance","title":"Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells","arxiv_id":"1802.07465","date":"2018-02-21","proceeding":null,"authors":["Fidel A. Guerrero-Pena","Pedro D. Marrero Fernandez","Tsang Ing Ren","Mary Yui","Ellen Rothenberg","Alexandre Cunha"],"abstract":"We propose a new multiclass weighted loss function for instance segmentation\nof cluttered cells. We are primarily motivated by the need of developmental\nbiologists to quantify and model the behavior of blood T-cells which might help\nus in understanding their regulation mechanisms and ultimately help researchers\nin their quest for developing an effective immuno-therapy cancer treatment.\nSegmenting individual touching cells in cluttered regions is challenging as the\nfeature distribution on shared borders and cell foreground are similar thus\ndifficulting discriminating pixels into proper classes. We present two novel\nweight maps applied to the weighted cross entropy loss function which take into\naccount both class imbalance and cell geometry. Binary ground truth training\ndata is augmented so the learning model can handle not only foreground and\nbackground but also a third touching class. This framework allows training\nusing U-Net. Experiments with our formulations have shown superior results when\ncompared to other similar schemes, outperforming binary class models with\nsignificant improvement of boundary adequacy and instance detection. We\nvalidate our results on manually annotated microscope images of T-cells.","url_abs":"http://arxiv.org/abs/1802.07465v1","url_pdf":"http://arxiv.org/pdf/1802.07465v1.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":"multiclass-weighted-loss-for-instance","repo_url":"https://github.com/SonwYang/building-extraction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"multiclass-weighted-loss-for-instance","repo_url":"https://github.com/juglab/VoidSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"concatenated-skip-connection","method_name":"Concatenated Skip Connection"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"u-net","method_name":"U-Net"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}