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
Proceedings ArticleDOI
Natural Adversarial Examples
TL;DR: In this article, the authors introduce two challenging datasets that reliably cause machine learning model performance to substantially degrade, and they also curate an adversarial out-of-distribution detection dataset called IMAGENET-O. The datasets are collected with a simple adversarial filtration technique to create datasets with limited spurious cues.
Posted Content
Scaling Vision Transformers
TL;DR: In this article, the authors investigate the relationship between the error rate, data, and compute of the Vision Transformer (ViT) model and obtain state-of-the-art performance.
Posted Content
3D Human Pose Estimation with Spatial and Temporal Transformers.
TL;DR: Poseformer as discussed by the authors is a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved and achieves state-of-the-art performance on two popular and standard benchmark datasets.
Proceedings ArticleDOI
Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos
TL;DR: Point 4D Transformer (P4Transformer) as discussed by the authors is a point 4D convolutional neural network that embeds the spatio-temporal local structures presented in a point cloud video and performs self-attention on the embedded local features.
Posted Content
ResMLP: Feedforward networks for image classification with data-efficient training
Hugo Touvron,Piotr Bojanowski,Mathilde Caron,Matthieu Cord,Alaaeldin El-Nouby,Edouard Grave,Armand Joulin,Gabriel Synnaeve,Jakob Verbeek,Hervé Jégou +9 more
TL;DR: ResMLP as mentioned in this paper is an architecture built entirely upon multi-layer perceptrons for image classification, which achieves surprisingly good accuracy/complexity trade-offs on ImageNet by using heavy data-augmentation and optionally distillation.
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.