SiT: Self-supervised vIsion Transformer

by   Sara Atito, et al.

Self-supervised learning methods are gaining increasing traction in computer vision due to their recent success in reducing the gap with supervised learning. In natural language processing (NLP) self-supervised learning and transformers are already the methods of choice. The recent literature suggests that the transformers are becoming increasingly popular also in computer vision. So far, the vision transformers have been shown to work well when pretrained either using a large scale supervised data or with some kind of co-supervision, e.g. in terms of teacher network. These supervised pretrained vision transformers achieve very good results in downstream tasks with minimal changes. In this work we investigate the merits of self-supervised learning for pretraining image/vision transformers and then using them for downstream classification tasks. We propose Self-supervised vIsion Transformers (SiT) and discuss several self-supervised training mechanisms to obtain a pretext model. The architectural flexibility of SiT allows us to use it as an autoencoder and work with multiple self-supervised tasks seamlessly. We show that a pretrained SiT can be finetuned for a downstream classification task on small scale datasets, consisting of a few thousand images rather than several millions. The proposed approach is evaluated on standard datasets using common protocols. The results demonstrate the strength of the transformers and their suitability for self-supervised learning. We outperformed existing self-supervised learning methods by large margin. We also observed that SiT is good for few shot learning and also showed that it is learning useful representation by simply training a linear classifier on top of the learned features from SiT. Pretraining, finetuning, and evaluation codes will be available under:


page 3

page 4

page 7

page 10


Self-Supervised Learning with Swin Transformers

We are witnessing a modeling shift from CNN to Transformers in computer ...

AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing

Transformer-based pretrained language models (T-PTLMs) have achieved gre...

An Empirical Study Of Self-supervised Learning Approaches For Object Detection With Transformers

Self-supervised learning (SSL) methods such as masked language modeling ...

Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformers

Automatic data augmentation (AutoAugment) strategies are indispensable i...

XTab: Cross-table Pretraining for Tabular Transformers

The success of self-supervised learning in computer vision and natural l...

LaCViT: A Label-aware Contrastive Training Framework for Vision Transformers

Vision Transformers have been incredibly effective when tackling compute...

How Useful is Self-Supervised Pretraining for Visual Tasks?

Recent advances have spurred incredible progress in self-supervised pret...

Please sign up or login with your details

Forgot password? Click here to reset