Deep Collaborative Learning for Visual Recognition

TL;DR

This paper introduces Deep Collaborative Learning (DCL), a novel method that reduces model complexity in deep neural networks for visual recognition by efficiently learning compositional visual concepts, leading to improved accuracy and fewer parameters.

Contribution

DCL replaces traditional convolutional layers with a two-stage module that models feature co-occurrence, increasing vocabulary size exponentially with linear growth in complexity.

Findings

DCL improves recognition accuracy across multiple datasets.

DCL reduces model parameters significantly, e.g., 16.82% fewer in AlexNet.

DCL is effective on various network architectures.

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).