{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T16:27:22Z","timestamp":1726849642219},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,7]]},"abstract":"<jats:p>Softmax loss is arguably one of the most popular losses to train CNN models for image classification. However, recent works have exposed its limitation on feature discriminability. This paper casts a new viewpoint on the weakness of softmax loss. On the one hand, the CNN features learned using the softmax loss are often inadequately discriminative. We hence introduce a soft-margin softmax function to explicitly encourage the discrmination between different classes. On the other hand, the learned classifier of softmax loss is weak. We propose to assemble multiple these weak classifiers to a strong one, inspired by the recognition that the diversity among weak classifiers is critical to a good ensemble. To achieve the diversity, we adopt the Hilbert-Schmidt Independence Criterion (HSIC). Considering these two aspects in one framework, we design a novel loss, named as Ensemble Soft-Margin Softmax (EM-Softmax). Extensive experiments on benchmark datasets are conducted to show the superiority of our design over the baseline softmax loss and several state-of-the-art alternatives.<\/jats:p>","DOI":"10.24963\/ijcai.2018\/138","type":"proceedings-article","created":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:49:10Z","timestamp":1530755350000},"page":"992-998","source":"Crossref","is-referenced-by-count":26,"title":["Ensemble Soft-Margin Softmax Loss for Image Classification"],"prefix":"10.24963","author":[{"given":"Xiaobo","family":"Wang","sequence":"first","affiliation":[{"name":"CBSR&NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China."}]},{"given":"Shifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"CBSR&NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China."}]},{"given":"Zhen","family":"Lei","sequence":"additional","affiliation":[{"name":"CBSR&NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China."}]},{"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Beihang University, Beijing, China"}]},{"given":"Xiaojie","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Computer Software, Tianjin University, Tianjin, China"}]},{"given":"Stan Z.","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Macau University of Science and Technology, Macau, China"},{"name":"CBSR&NLPR, Institute of Automation, Chinese Academy of Sciences, Beijing, China"},{"name":"University of Chinese Academy of Sciences, Beijing, China."}]}],"member":"10584","event":{"number":"27","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2018","name":"Twenty-Seventh International Joint Conference on Artificial Intelligence {IJCAI-18}","start":{"date-parts":[[2018,7,13]]},"theme":"Artificial Intelligence","location":"Stockholm, Sweden","end":{"date-parts":[[2018,7,19]]}},"container-title":["Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2018,7,5]],"date-time":"2018-07-05T01:50:18Z","timestamp":1530755418000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2018\/138"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2018,7]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2018\/138","relation":{},"subject":[],"published":{"date-parts":[[2018,7]]}}}