The human vision system usually has a specifically activated area of neurons when recognizing a category of images. Inspired by this visual mechanism, we propose a layerwise class-aware convolutional neural network architecture to explicitly discover category-tailored neurons on intermediate hidden layers to improve the network learning ability. Instead of directly selecting activated neurons for different categories, we inversely suppress those neurons of intermediate layers irrelevant with the given target class to produce a class-specific subnetwork, which implicitly enhances the discriminability of hidden layer features due to the increase of the inter-class discrepancy on them. Together with the classifier of the top layer, we jointly learn this network by formulating the suppressor of hidden layers as a penalty term in the objective function. To address class-specific neuron suppression in each hidden layer, we also introduce a statistic method based on mutual information to dynamically and automatically update the suppressed neurons during the network training. Extensive experiments demonstrate that the proposed model is superior to the state-of-the-art models.

+More

vision system stateoftheart models objective layerwise classaware convolutional neural network architecture area categorytailored neurons discriminability of hidden layer features model classifier interclass discrepancy on classspecific neuron suppression statistic method mutual information network learning

Shuicheng Yan,Zhen Cui, Zhiheng Niu, Luoqi Liu,.Layerwise Class-Aware Convolutional Neural Network. 27 (12),2601-2612.

Shuicheng Yan, et al."Layerwise Class-Aware Convolutional Neural Network" 27

Shuicheng Yan,Zhen Cui, Zhiheng Niu, Luoqi Liu,"Layerwise Class-Aware Convolutional Neural Network"