Deep Collaborative Learning for Visual Recognition

Abstract

Deep neural networks are playing an important role in state-of-the-art visual recognition. To represent high-level visual concepts, modern networks are equipped with large convolutional layers, which use a large number of filters and contribute significantly to model complexity. For example, more than half of the weights of AlexNet are stored in the first fully-connected layer (4,096 filters). We formulate the function of a convolutional layer as learning a large visual vocabulary, and propose an alternative way, namely Deep Collaborative Learning (DCL), to reduce the computational complexity. We replace a convolutional layer with a two-stage DCL module, in which we first construct a couple of smaller convolutional layers individually, and then fuse them at each spatial position to consider feature co-occurrence. In mathematics, DCL can be explained as an efficient way of learning compositional visual concepts, in which the vocabulary size increases exponentially while the model complexity only increases linearly. We evaluate DCL on a wide range of visual recognition tasks, including a series of multi-digit number classification datasets, and some generic image classification datasets such as SVHN, CIFAR and ILSVRC2012. We apply DCL to several state-of-the-art network structures, improving the recognition accuracy meanwhile reducing the number of parameters (16.82% fewer in AlexNet).

arXiv commentSubmitted to CVPR 2017 (10 pages, 5 figures)

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Improving neural networks by preventing co-adaptation of feature detectors
• Deep Residual Learning for Image Recognition
• Wide Residual Networks
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Stochastic Pooling for Regularization of Deep Convolutional Neural Networks
• Neural Activation Constellations: Unsupervised Part Model Discovery with Convolutional Networks
• Unsupervised learning of object semantic parts from internal states of CNNs by population encoding
• Parsing Occluded People by Flexible Compositions