scispace - formally typeset
Open AccessProceedings Article

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

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

Content maybe subject to copyright    Report

Citations
More filters
Posted Content

Probabilistic Approach for Road-Users Detection

TL;DR: In this article, a probabilistic layer is introduced to deep object detection networks in testing to avoid the traditional Sigmoid or Softmax prediction layer which often produces overconfident predictions.
Posted Content

How to Train Your MAML to Excel in Few-Shot Classification

TL;DR: UNICORN-MAML as mentioned in this paper is a few-shot meta-learning algorithm that uses a shared classifier initialization for all the classes in order to solve the problem of permutation invariance.
Posted Content

SWAT: Spatial Structure Within and Among Tokens

TL;DR: In this article, Structure-Aware Tokenization and Structure-aware Mixing (SWAT) is proposed to preserve the spatial structure of the image patches in the mixing stage.
Posted Content

Improved Transformer for High-Resolution GANs

TL;DR: Huang et al. as mentioned in this paper proposed a multi-axis blocked self-attention which allows efficient mixing of local and global attention for high-resolution image generation based on Generative Adversarial Networks.
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

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.
Related Papers (5)