Can We Gain More from Orthogonality Regularizations in Training Deep CNNs?
This work addresses the need for better training stability and accuracy in deep learning models, particularly for computer vision tasks, but it is incremental as it builds on existing orthogonality regularization methods.
The paper tackled the problem of enforcing orthogonality in deep CNNs more effectively, resulting in consistent performance gains including improved final accuracies and faster, more stable convergence on benchmarks like ResNet and ImageNet.
This paper seeks to answer the question: as the (near-) orthogonality of weights is found to be a favorable property for training deep convolutional neural networks, how can we enforce it in more effective and easy-to-use ways? We develop novel orthogonality regularizations on training deep CNNs, utilizing various advanced analytical tools such as mutual coherence and restricted isometry property. These plug-and-play regularizations can be conveniently incorporated into training almost any CNN without extra hassle. We then benchmark their effects on state-of-the-art models: ResNet, WideResNet, and ResNeXt, on several most popular computer vision datasets: CIFAR-10, CIFAR-100, SVHN and ImageNet. We observe consistent performance gains after applying those proposed regularizations, in terms of both the final accuracies achieved, and faster and more stable convergences. We have made our codes and pre-trained models publicly available: https://github.com/nbansal90/Can-we-Gain-More-from-Orthogonality.