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
BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search
TL;DR: In this paper, a blockwise self-supervised neural architecture search (BossNAS) method is proposed to address the problem of inaccurate architecture rating caused by large weight-sharing space and biased supervision.
Posted Content
Dynamic Neural Networks: A Survey
TL;DR: In this paper, the authors comprehensively review the rapidly developing area by dividing dynamic networks into three main categories: 1) instance-wise dynamic models that process each instance with data-dependent architectures or parameters; 2) spatialwise dynamic networks that conduct adaptive computation with respect to different spatial locations of image data and 3) temporal-wise DNNs that perform adaptive inference along the temporal dimension for sequential data such as videos and texts.
Posted Content
TransReID: Transformer-based Object Re-Identification
TL;DR: TransReID as mentioned in this paper proposes a pure transformer-based object ReID framework, which first encodes an image as a sequence of patches and builds a transformerbased strong baseline with a few critical improvements, which achieves competitive results on several ReID benchmarks.
Journal Article
Multi-Head Attention: Collaborate Instead of Concatenate
TL;DR: A collaborative multi-head attention layer that enables heads to learn shared projections and improves the computational cost and number of parameters in an attention layer and can be used as a drop-in replacement in any transformer architecture.
Journal ArticleDOI
TransRPPG: Remote Photoplethysmography Transformer for 3D Mask Face Presentation Attack Detection
TL;DR: Wang et al. as discussed by the authors proposed a pure remote photoplethysmography transformer (TransRPPG) framework for learning intrinsic liveness representation efficiently, which is lightweight and efficient (with only 547 K parameters and 763 M FLOPs).
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.