{"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/contrastive-center-loss-for-deep-neural","title":"Contrastive-center loss for deep neural networks","arxiv_id":"1707.07391","date":"2017-07-24","proceeding":null,"authors":["Ce Qi","Fei Su"],"abstract":"The deep convolutional neural network(CNN) has significantly raised the\nperformance of image classification and face recognition. Softmax is usually\nused as supervision, but it only penalizes the classification loss. In this\npaper, we propose a novel auxiliary supervision signal called contrastivecenter\nloss, which can further enhance the discriminative power of the features, for\nit learns a class center for each class. The proposed contrastive-center loss\nsimultaneously considers intra-class compactness and inter-class separability,\nby penalizing the contrastive values between: (1)the distances of training\nsamples to their corresponding class centers, and (2)the sum of the distances\nof training samples to their non-corresponding class centers. Experiments on\ndifferent datasets demonstrate the effectiveness of contrastive-center loss.","url_abs":"http://arxiv.org/abs/1707.07391v2","url_pdf":"http://arxiv.org/pdf/1707.07391v2.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":"contrastive-center-loss-for-deep-neural","repo_url":"https://github.com/Mungosin/Mozgalo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1707.07391","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}