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
Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis
TL;DR: DietNeRF as discussed by the authors introduces an auxiliary semantic consistency loss that encourages realistic renderings at novel poses, which is trained on individual scenes to correctly render given input views from the same pose and match high-level semantic attributes across different, random poses.
Proceedings ArticleDOI
H-GAN: the power of GANs in your Hands
Sergiu Oprea,Giorgos Karvounas,Pablo Martinez-Gonzalez,Nikolaos Kyriazis,Sergio Orts-Escolano,Iason Oikonomidis,Alberto Garcia-Garcia,Aggeliki Tsoli,Jose Garcia-Rodriguez,Antonis A. Argyros +9 more
TL;DR: HandGAN as discussed by the authors is a cycle-consistent adversarial learning approach implementing multi-scale perceptual discriminators, which is designed to translate synthetic images of hands to the real domain by improving the appearance of synthetic hands to approximate the statistical distribution underlying a collection of real images.
Posted Content
BoxeR: Box-Attention for 2D and 3D Transformers.
TL;DR: Zhang et al. as discussed by the authors proposed a simple attention mechanism, called Box-Attention, which enables spatial interaction between grid features, as sampled from boxes of interest, and improves the learning capability of transformers for several vision tasks.
Book ChapterDOI
A Deep Attention Transformer Network for Pain Estimation with Facial Expression Video.
Haochen Xu,Manhua Liu +1 more
TL;DR: Li et al. as mentioned in this paper proposed a deep attention transformer network for pain estimation called Pain Estimate Transformer (PET), which consists of two different subnetworks: an image encoding subnetwork and a video transformer subnetwork.
Posted Content
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques.
Shiyu Tang,Ruihao Gong,Yan Wang,Aishan Liu,Jiakai Wang,Xinyun Chen,Fengwei Yu,Xianglong Liu,Dawn Song,Alan L. Yuille,Philip H. S. Torr,Dacheng Tao +11 more
TL;DR: In this article, the authors proposed RobustART, the first comprehensive robustness investigation benchmark on ImageNet (including open-source toolkit, pre-trained model zoo, datasets, and analyses) regarding ARchitecture design and general training techniques.
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.