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
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
Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
TL;DR: In-Time Over-Parameterization (ITOP) as mentioned in this paper is a new perspective on training deep neural networks capable of state-of-the-art performance without the need for the expensive over-parameterization.
Posted Content
A Fast Partial Video Copy Detection Using KNN and Global Feature Database.
TL;DR: In this paper, a fast partial video copy detection framework is proposed, where all frame features of the reference videos are organized in a KNN searchable database and a modified temporal network is used to localize the copy segment in the candidate videos.
Book ChapterDOI
Prediction of Epiretinal Membrane from Retinal Fundus Images Using Deep Learning
Ángela Casado-García,Manuel García-Domínguez,Jónathan Heras,Adrián Inés,Didac Royo,Miguel A Zapata +5 more
TL;DR: In this paper, the authors conducted a thorough study of several deep learning architectures, and a variety of techniques to train them, in order to build a model for automatically diagnosing epiretinal membrane (ERM) disease.
Posted Content
Adaptive Hierarchical Dual Consistency for Semi-Supervised Left Atrium Segmentation on Cross-Domain Data
TL;DR: Adaptive Hierarchical Dual Consistency (AHDC) as mentioned in this paper is proposed for semi-supervised segmentation on cross-domain data, which consists of a bidirectional adversarial inference module (BAI) and a hierarchical dual consistency learning module (HDC).
Posted Content
Pix2seq: A Language Modeling Framework for Object Detection
TL;DR: Pix2Seq as mentioned in this paper cast object detection as a language modeling task conditioned on the observed pixel inputs, where object descriptions (e.g., bounding boxes and class labels) are expressed as sequences of discrete tokens and train a neural network to perceive the image and generate the desired sequence.
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.