Deeply-Supervised Nets
This addresses the need for more transparent and effective training in deep learning, particularly for computer vision tasks, though it is incremental as it builds on existing CNN architectures.
The paper tackles the problem of improving classification performance and training transparency in deep convolutional neural networks by introducing deeply-supervised nets with companion objectives for hidden layers, achieving state-of-the-art results on benchmark datasets like MNIST, CIFAR-10, CIFAR-100, and SVHN.
Our proposed deeply-supervised nets (DSN) method simultaneously minimizes classification error while making the learning process of hidden layers direct and transparent. We make an attempt to boost the classification performance by studying a new formulation in deep networks. Three aspects in convolutional neural networks (CNN) style architectures are being looked at: (1) transparency of the intermediate layers to the overall classification; (2) discriminativeness and robustness of learned features, especially in the early layers; (3) effectiveness in training due to the presence of the exploding and vanishing gradients. We introduce "companion objective" to the individual hidden layers, in addition to the overall objective at the output layer (a different strategy to layer-wise pre-training). We extend techniques from stochastic gradient methods to analyze our algorithm. The advantage of our method is evident and our experimental result on benchmark datasets shows significant performance gain over existing methods (e.g. all state-of-the-art results on MNIST, CIFAR-10, CIFAR-100, and SVHN).