{"type":"ScholarlyArticle","title":"Improving CNN Performance with Min-Max Objective","authors":[{"name":"Weiwei Shi","slug":"weiwei-shi","given":"Weiwei","family":"Shi","affiliation":""},{"name":"Yihong Gong","slug":"yihong-gong","given":"Yihong","family":"Gong","affiliation":""},{"name":"Jinjun Wang","slug":"jinjun-wang","given":"Jinjun","family":"Wang","affiliation":""}],"abstract":"In this paper, we propose a novel method to improve object recognition accuracies of convolutional neural networks (CNNs) by embedding the proposed Min-Max objective into a high layer of the models during the training process. The Min-Max objective explicitly enforces the learned object feature maps to have the minimum compactness for each object manifold and the maximum margin between different object manifolds. The Min-Max objective can be universally applied to different CNN models with negligible additional computation cost. Experiments with shallow and deep models on four benchmark datasets including CIFAR-10, CIFAR-100, SVHN and MNIST demonstrate that CNN models trained with the Min-Max objective achieve remarkable performance improvements compared to the corresponding baseline models.","doi":null,"url":"https://ijcai.org/proceedings/2016/286","pdf":"https://ijcai.org/proceedings/2016/0286.pdf","markdown":"https://ijcai.org/proceedings/2016/286.md","bibtex":"https://ijcai.org/proceedings/2016/bibtex/286","volume":{"slug":"2016","title":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2016","url":"https://ijcai.org/proceedings/2016/","year":2016,"location":"New York, NY, USA","dates":"9–15 July 2016","editors":"Subbarao Kambhampati","isbn":"978-1-57735-770-4; 978-1-57735-771-1","publisher":"AAAI Press / International Joint Conferences on Artificial Intelligence","doi_prefix":""},"section":null,"track":"","number":286,"pages":{"first":2004,"last":2009},"keywords":[],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}