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
Journal ArticleDOI
Emerging trends: A gentle introduction to fine-tuning
TL;DR: In this paper, the authors make fine-tuning more accessible to a broader audience by using pre-trained models and using a small training set of labeled data to produce a model for downstream applications.
Proceedings ArticleDOI
Rethinking the Self-Attention in Vision Transformers
TL;DR: In this paper, the authors show that self-attention in vision transformer inference is extremely sparse and propose to apply a sparsity constraint to the selfattention maps, which can achieve 95% sparsity on the self attention maps while maintaining the performance drop.
Posted Content
Robust fine-tuning of zero-shot models
Mitchell Wortsman,Gabriel Ilharco,Mike Li,Jong Wook Kim,Hannaneh Hajishirzi,Ali Farhadi,Hongseok Namkoong,Ludwig Schmidt +7 more
TL;DR: Weight-space ensembles as mentioned in this paper ensembling the weights of the zero-shot and fine-tuned models provide large accuracy improvements out-of-distribution, while matching or improving in-disparity accuracy.
Posted Content
Point Transformer.
TL;DR: The Point Transformer design improves upon prior work across domains and tasks and crosses the 70% mIoU threshold for the first time on the challenging S3DIS dataset.
Posted Content
Container: Context Aggregation Network
TL;DR: In this paper, a general-purpose building block for multi-head context aggregation is proposed, which can exploit long-range interactions between Transformers while still exploiting the inductive bias of the local convolution operation leading to faster convergence speeds.
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.