Data-dependent initializations of convolutional neural networks

Philipp Krähenbühl, Carl Doersch, Jeff Donahue and Trevor Darrell
ICLR 2016
[pdf] [code] [py-faster-rcnn training scripts]

Convolutional Neural Networks spread through computer vision like a wildfire, impacting almost all visual tasks imaginable. Despite this, few researchers dare to train their models from scratch. Most work builds on one of a handful of ImageNet pre-trained models, and fine-tunes or adapts these for specific tasks. This is in large part due to the difficulty of properly initializing these networks from scratch. A small miscalibration of the initial weights leads to vanishing or exploding gradients, as well as poor convergence properties. In this work we present a fast and simple data-dependent initialization procedure, that sets the weights of a network such that all units in the network train at roughly the same rate, avoiding vanishing or exploding gradients. Our initialization matches the current state-of-the-art unsupervised or self-supervised pre-training methods on standard computer vision tasks, such as image classification and object detection, while reducing the pre-training time by three orders of magnitude. When combined with pre-training methods, our initialization significantly outperforms prior work, narrowing the gap between supervised and unsupervised pre-training.