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
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Hwanjun Song,Deqing Sun,Sanghyuk Chun,Varun Jampani,Dongyoon Han,Byeongho Heo,Wonjae Kim,Ming-Hsuan Yang +7 more
TL;DR: In this article, the authors integrate vision and detection transformers (ViDT) to build an effective and efficient object detector, which introduces a reconfigured attention module to extend the recent Swin Transformer to be a standalone object detector.
Posted Content
Shifted Chunk Transformer for Spatio-Temporal Representational Learning
TL;DR: In this article, a shifted chunk Transformer with pure self-attention blocks is proposed to learn hierarchical spatio-temporal features from a local tiny patch to a global video clip.
Posted Content
Searching for TrioNet: Combining Convolution with Local and Global Self-Attention.
TL;DR: TrioNet as discussed by the authors combines convolution, local self-attention, and global selfattention operators with weight-sharing Neural Architecture Search (NAS) algorithms to explore a wider range of architecture space.
Posted Content
PTQ4ViT: Post-Training Quantization Framework for Vision Transformers
TL;DR: Zhang et al. as discussed by the authors proposed the twin uniform quantization method to reduce the quantization error on these activation values and used a Hessian guided metric to evaluate different scaling factors to improve the accuracy of calibration with a small cost.
Posted Content
SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentation
TL;DR: Zhang et al. as mentioned in this paper improved standard positional encoding by introducing the concept of Relative Positional Encoding, which integrates spatial information at the feature level and can handle arbitrary image sizes.
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.