Proceedings

Improving CNN Performance with Min-Max Objective

Weiwei Shi, Yihong Gong, Jinjun Wang

Download BibTeX Cite

Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 2004-2009.

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.

Weiwei Shi, Yihong Gong, and Jinjun Wang. 2016. Improving CNN Performance with Min-Max Objective. In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16. IJCAI, 2004–2009. https://ijcai.org/proceedings/2016/286
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards