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
CLIP Meets Video Captioners: Attribute-Aware Representation Learning Promotes Accurate Captioning.
Bang Yang,Yuexian Zou +1 more
TL;DR: In this article, dual attribute prediction is introduced to learn the correspondence between video content and attributes and the co-occurrence relations between attributes. But it is difficult to capture attributes' semantics and sensitive to irrelevant background information.
Posted Content
CyTran: Cycle-Consistent Transformers for Non-Contrast to Contrast CT Translation.
Nicolae-Catalin Ristea,Andreea-Iuliana Miron,Olivian Savencu,Mariana-Iuliana Georgescu,Nicolae Verga,Fahad Shahbaz Khan,Radu Tudor Ionescu +6 more
TL;DR: In this article, a cycle-consistent generative adversarial convolutional transformers (CyTran) is proposed to translate unpaired contrast computed tomography (CT) scans to non-contrast CT scans and the other way around.
Posted Content
PETA: Photo Albums Event Recognition using Transformers Attention.
TL;DR: Wang et al. as discussed by the authors combine the power of CNNs for image representation and transformers for album representation to perform global reasoning on image collection, offering a practical and efficient solution for photo albums event recognition.
Posted Content
Blending Anti-Aliasing into Vision Transformer.
TL;DR: Aliasing effect occurs when discrete patterns are used to produce high frequency or continuous information, resulting in the indistinguishable distortions as discussed by the authors, which is the traditional problem of aliasing for vision transformers.
Posted Content
TransMix: Attend to Mix for Vision Transformers.
TL;DR: TransMix as mentioned in this paper proposes to use the attention maps of Vision Transformers to bridge the gap between the input and label spaces, which can consistently improve various ViT-based models at scales on ImageNet classification.
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.