# Improving Resnet-9 Generalization Trained on Small Datasets Source: [Improving Resnet-9 Generalization Trained on Small Datasets]() Collection index: [llms.txt]() Data updated: 2025-10-26T04:47:07.371Z Authors: Omar Mohamed Awad, Habib Hajimolahoseini, Michael Lim, Gurpreet Gosal, Walid Ahmed, Yang Liu, Gordon Deng Published: 2023-09-07T18:46:52.000Z ## Abstract This paper presents our proposed approach that won the first prize at the ICLR competition on Hardware Aware Efficient Training. The challenge is to achieve the highest possible accuracy in an image classification task in less than 10 minutes. The training is done on a small dataset of 5000 images picked randomly from CIFAR-10 dataset. The evaluation is performed by the competition organizers on a secret dataset with 1000 images of the same size. Our approach includes applying a series of technique for improving the generalization of ResNet-9 including: sharpness aware optimization, label smoothing, gradient centralization, input patch whitening as well as metalearning based training. Our experiments show that the ResNet-9 can achieve the accuracy of 88% while trained only on a 10% subset of CIFAR-10 dataset in less than 10 minuets ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()