Semi-Supervised Vision Transformers

Abstract

We study the training of Vision Transformers for semi-supervised image classification. Transformers have recently demonstrated impressive performance on a multitude of supervised learning tasks. Surprisingly, we show Vision Transformers perform significantly worse than Convolutional Neural Networks when only a small set of labeled data is available. Inspired by this observation, we introduce a joint semi-supervised learning framework, Semiformer, which contains a transformer stream, a convolutional stream and a carefully designed fusion module for knowledge sharing between these streams. The convolutional stream is trained on limited labeled data and further used to generate pseudo labels to supervise the training of the transformer stream on unlabeled data. Extensive experiments on ImageNet demonstrate that Semiformer achieves 75.5% top-1 accuracy, outperforming the state-of-the-art by a clear margin. In addition, we show, among other things, Semiformer is a general framework that is compatible with most modern transformer and convolutional neural architectures. Code is available at https://github.com/wengzejia1/Semiformer.

16 pages, 4 figures, ECCV 2022

References in corpus (8)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• Conformer: Convolution-augmented Transformer for Speech Recognition
• Learning with Pseudo-Ensembles
• Early Convolutions Help Transformers See Better
• Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition
• CvT: Introducing Convolutions to Vision Transformers
• ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring
• Rethinking Spatial Dimensions of Vision Transformers