Proceedings Abstracts of the Twenty-Fifth International Joint Conference on Artificial Intelligence

Improving CNN Performance with Min-Max Objective / 2004
Weiwei Shi, Yihong Gong, Jinjun Wang

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.