Fixing the train-test resolution discrepancy

TL;DR

This paper addresses the resolution discrepancy between training and testing in image classification, proposing a simple fine-tuning method to improve performance, enabling training with smaller images and achieving state-of-the-art results.

Contribution

It introduces an efficient fine-tuning strategy to optimize classifier performance across different resolutions, allowing effective training with smaller images and achieving high accuracy on ImageNet.

Findings

Lower train resolution can improve test accuracy.

Test resolution fine-tuning enhances classifier performance.

Achieved state-of-the-art ImageNet accuracy with resolution optimization.

Abstract

Data-augmentation is key to the training of neural networks for image classification. This paper first shows that existing augmentations induce a significant discrepancy between the typical size of the objects seen by the classifier at train and test time. We experimentally validate that, for a target test resolution, using a lower train resolution offers better classification at test time. We then propose a simple yet effective and efficient strategy to optimize the classifier performance when the train and test resolutions differ. It involves only a computationally cheap fine-tuning of the network at the test resolution. This enables training strong classifiers using small training images. For instance, we obtain 77.1% top-1 accuracy on ImageNet with a ResNet-50 trained on 128x128 images, and 79.8% with one trained on 224x224 image. In addition, if we use extra training data we get 82.5% with the ResNet-50 train with 224x224 images. Conversely, when training a ResNeXt-101 32x48d pre-trained in weakly-supervised fashion on 940 million public images at resolution 224x224 and further optimizing for test resolution 320x320, we obtain a test top-1 accuracy of 86.4% (top-5: 98.0%) (single-crop). To the best of our knowledge this is the highest ImageNet single-crop, top-1 and top-5 accuracy to date.