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
How Transferable are Reasoning Patterns in VQA
Corentin Kervadec,Theo Jaunet,Grigory Antipov,Moez Baccouche,Romain Vuillemot,Christian Wolf +5 more
TL;DR: In this article, the authors train a visual oracle and compare it with a SOTA Transformer-based model for VQA, showing that the former is much less prone to exploiting spurious dataset biases compared to the latter.
Posted Content
GMFlow: Learning Optical Flow via Global Matching
TL;DR: In this article, the authors propose a GMFlow framework, which consists of three main components: a customized Transformer for feature enhancement, a correlation and softmax layer for global feature matching, and a self-attention layer for flow propagation.
Posted Content
Segmenter: Transformer for Semantic Segmentation
TL;DR: Segmenter as mentioned in this paper is a transformer model for semantic segmentation, which allows to model global context already at the first layer and throughout the network, and achieves state-of-the-art performance on the challenging ADE20K dataset.
Posted Content
Training Vision Transformers for Image Retrieval
TL;DR: In this article, a transformer-based approach for image retrieval is proposed, which combines a contrastive loss with a differential entropy regularizer to generate image descriptors and train the resulting model with a metric learning objective.
Posted Content
XCiT: Cross-Covariance Image Transformers.
Alaaeldin El-Nouby,Hugo Touvron,Mathilde Caron,Piotr Bojanowski,Matthijs Douze,Armand Joulin,Ivan Laptev,Natalia Neverova,Gabriel Synnaeve,Jakob Verbeek,Hervé Jégou +10 more
TL;DR: Cross-covariance image transformer (XCiT) as mentioned in this paper proposes a cross-cavariance attention (XCA) operation that operates across feature channels rather than tokens, where the interactions are based on the crosscovarisance matrix between keys and queries.
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.