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
Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers
TL;DR: In this paper, a token-based generator is proposed to learn content-aware and fine-grained style control for image synthesis, which takes as input a sequence of latent tokens to predict the visual tokens for synthesizing an image.
Posted Content
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer
Sachin Mehta,Mohammad Rastegari +1 more
TL;DR: MobileViT as discussed by the authors combines the strengths of CNNs and self-attention-based vision trans-formers to build a light-weight and low latency network for mobile vision tasks.
Posted Content
Intuitive and Efficient Roof Modeling for Reconstruction and Synthesis
TL;DR: In this article, a graph structure is used to encode roof topology and enforces the roof validity by optimizing a simple but effective planarity metric, which can accommodate different styles and user preferences for roof modeling.
Posted Content
Donut: Document Understanding Transformer without OCR
Geewook Kim,Teakgyu Hong,Moonbin Yim,Jin Young Park,Jinyeong Yim,Wonseok Hwang,Sangdoo Yun,Dongyoon Han,Seunghyun Park +8 more
TL;DR: In this article, the authors propose a novel VDU model that is end-to-end trainable without underpinning OCR framework and a synthetic document image generator to pre-train the model to mitigate the dependencies on large-scale real document images.
Posted Content
Spectral Transform Forms Scalable Transformer
TL;DR: In this paper, a spectral window unit (SWINIT) model is proposed to predict scalable dynamic graphs with assured efficiency, which is assembled with a few simple effective computational blocks that constitute randomized SVD, MLP, and graph Framelet convolution.
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.