Going deeper with Image Transformers
Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so far. In this work, we build and optimize deeper transformer networks for image classification. In particular, we investigate the interplay of architecture and optimization of such dedicated transformers. We make two transformers architecture changes that significantly improve the accuracy of deep transformers. This leads us to produce models whose performance does not saturate early with more depth, for instance we obtain 86.5% top-1 accuracy on Imagenet when training with no external data, we thus attain the current SOTA with less FLOPs and parameters. Moreover, our best model establishes the new state of the art on Imagenet with Reassessed labels and Imagenet-V2 / match frequency, in the setting with no additional training data. We share our code and models.
PDF Abstract ICCV 2021 PDF ICCV 2021 AbstractCode
Colab
CIFAR-10
ImageNet
CIFAR-100
Oxford 102 Flower
Stanford Cars
iNaturalist
Results from the Paper
Ranked #5 on
Image Classification
on CIFAR-10
(using extra training data)
