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
Smart Bird: Learnable Sparse Attention for Efficient and Effective Transformer
TL;DR: In this paper, the authors propose Smart Bird, which is an efficient and effective Transformer with learnable sparse attention, which aims to find potential important interactions between tokens and select token embeddings according to the index matrices to form the input of sparse attention networks.
Posted Content
Relative Molecule Self-Attention Transformer
Łukasz Maziarka,Dawid Majchrowski,Tomasz Danel,Piotr Gaiński,Jacek Tabor,Igor T. Podolak,Pawel Morkisz,Stanisław Jastrzębski +7 more
TL;DR: The Relative Molecule Attention Transformer (R-MAT) as discussed by the authors is based on the self-attention mechanism and achieves state-of-the-art or very competitive results across a wide range of molecule property prediction tasks.
Posted Content
TransLoc3D : Point Cloud based Large-scale Place Recognition using Adaptive Receptive Fields.
TL;DR: TransLoc3D as mentioned in this paper adaptively adjusts the size of the receptive field based on the input point cloud and obtain discriminative global descriptors of point clouds for the place recognition task.
Posted Content
Dual-view Molecule Pre-training.
TL;DR: Dual-view molecule pre-training (DMP) as discussed by the authors combines the strengths of both types of molecule representations and achieves state-of-the-art performance on the USPTO full dataset.
Journal ArticleDOI
Improving the Authentication with Built-In Camera Protocol Using Built-In Motion Sensors: A Deep Learning Solution
TL;DR: In this article, the authors proposed an enhanced version of the authentication with built-in camera (ABC) protocol by employing a deep learning solution based on builtin motion sensors and applied Support Vector Machines for the smartphone identification task.
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.