Greedy Layerwise Learning Can Scale to ImageNet

TL;DR

This paper demonstrates that greedy layerwise training of CNNs using sequential auxiliary problems can scale to ImageNet, outperforming some traditional models and matching end-to-end training accuracy.

Contribution

It introduces a scalable layerwise training method for CNNs that achieves competitive performance on large-scale image classification tasks.

Findings

Exceeds AlexNet performance on ImageNet using layerwise training.

Constructs 11-layer networks surpassing VGG models.

Matches VGG-11 accuracy with end-to-end training.

Abstract

Shallow supervised 1-hidden layer neural networks have a number of favorable properties that make them easier to interpret, analyze, and optimize than their deep counterparts, but lack their representational power. Here we use 1-hidden layer learning problems to sequentially build deep networks layer by layer, which can inherit properties from shallow networks. Contrary to previous approaches using shallow networks, we focus on problems where deep learning is reported as critical for success. We thus study CNNs on image classification tasks using the large-scale ImageNet dataset and the CIFAR-10 dataset. Using a simple set of ideas for architecture and training we find that solving sequential 1-hidden-layer auxiliary problems lead to a CNN that exceeds AlexNet performance on ImageNet. Extending this training methodology to construct individual layers by solving 2-and-3-hidden layer auxiliary problems, we obtain an 11-layer network that exceeds several members of the VGG model family on ImageNet, and can train a VGG-11 model to the same accuracy as end-to-end learning. To our knowledge, this is the first competitive alternative to end-to-end training of CNNs that can scale to ImageNet. We illustrate several interesting properties of these models theoretically and conduct a range of experiments to study the properties this training induces on the intermediate layers.