ResBuilder: Automated Learning of Depth with Residual Structures
This work addresses the need for automated and efficient neural architecture design, particularly for image classification and industrial applications like fraud detection, though it is incremental as it builds on existing ResNet frameworks.
The authors tackled the problem of designing efficient ResNet architectures by developing ResBuilder, a neural architecture search algorithm that automatically constructs or modifies ResNet structures, achieving near state-of-the-art performance on image classification datasets while reducing computational costs.
In this work, we develop a neural architecture search algorithm, termed Resbuilder, that develops ResNet architectures from scratch that achieve high accuracy at moderate computational cost. It can also be used to modify existing architectures and has the capability to remove and insert ResNet blocks, in this way searching for suitable architectures in the space of ResNet architectures. In our experiments on different image classification datasets, Resbuilder achieves close to state-of-the-art performance while saving computational cost compared to off-the-shelf ResNets. Noteworthy, we once tune the parameters on CIFAR10 which yields a suitable default choice for all other datasets. We demonstrate that this property generalizes even to industrial applications by applying our method with default parameters on a proprietary fraud detection dataset.