Open AccessProceedings Article
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Alexey Dosovitskiy,Lucas Beyer,Alexander Kolesnikov,Dirk Weissenborn,Xiaohua Zhai,Thomas Unterthiner,Mostafa Dehghani,Matthias Minderer,Georg Heigold,Sylvain Gelly,Jakob Uszkoreit,Neil Houlsby +11 more
Reads0
Chats0
TLDR
The Vision Transformer (ViT) as discussed by the authors uses a pure transformer applied directly to sequences of image patches to perform very well on image classification tasks, achieving state-of-the-art results on ImageNet, CIFAR-100, VTAB, etc.Abstract:
While the Transformer architecture has become the de-facto standard for natural language processing tasks, its applications to computer vision remain limited. In vision, attention is either applied in conjunction with convolutional networks, or used to replace certain components of convolutional networks while keeping their overall structure in place. We show that this reliance on CNNs is not necessary and a pure transformer applied directly to sequences of image patches can perform very well on image classification tasks. When pre-trained on large amounts of data and transferred to multiple mid-sized or small image recognition benchmarks (ImageNet, CIFAR-100, VTAB, etc.), Vision Transformer (ViT) attains excellent results compared to state-of-the-art convolutional networks while requiring substantially fewer computational resources to train.read more
Citations
More filters
Posted Content
A Fine-Grained Analysis on Distribution Shift.
Olivia Wiles,Sven Gowal,Florian Stimberg,Sylvestre-Alvise Rebuffi,Ira Ktena,Krishnamurthy Dvijotham,A. Taylan Cemgil +6 more
TL;DR: Gulrajani et al. as discussed by the authors provided a holistic analysis of current state-of-the-art methods by evaluating 19 distinct methods grouped into five categories across both synthetic and real-world datasets.
Posted Content
Prioritized training on points that are learnable, worth learning, and not yet learned.
Sören Mindermann,Muhammed Razzak,Winnie Xu,Andreas Kirsch,Mrinank Sharma,Adrien Morisot,Aidan N. Gomez,Sebastian Farquhar,Jan Markus Brauner,Yarin Gal +9 more
TL;DR: Goldilocks Selection as discussed by the authors selects a sequence of training points that are "just right" to maximize the information about a validation set, which is a technique for faster model training.
Journal ArticleDOI
Can Vision Transformers Learn without Natural Images?
TL;DR: In this article , the results of formula-driven supervised learning (FDSL) framework are comparable with, and can even partially outperform, sophisticated self-supervised learning (SSL) methods like SimCLRv2 and MoCov2 without using any natural images in the pre-training phase.
Posted Content
Co-domain Symmetry for Complex-Valued Deep Learning.
TL;DR: In this article, complex-valued scaling is used as a co-domain transformation and the authors design novel equivariant and invariant neural network layer functions for this special transformation.
Posted Content
Going Beyond Linear Transformers with Recurrent Fast Weight Programmers
TL;DR: In this paper, a recurrent Fast Weight Programmer (RFWP) is proposed to add recurrence to the slow and fast nets of linear Transformers with linearised attention, which is more general than the linear Transformers.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings ArticleDOI
ImageNet: A large-scale hierarchical image database
TL;DR: A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Proceedings ArticleDOI
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
TL;DR: BERT as mentioned in this paper pre-trains deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.