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
Posted Content
A Practical Survey on Faster and Lighter Transformers.
TL;DR: This survey investigates popular approaches to make the Transformer faster and lighter and provides a comprehensive explanation of the methods' strengths, limitations, and underlying assumptions to meet the desired trade-off between capacity, computation, and memory.
Posted Content
Instance-level Image Retrieval using Reranking Transformers
TL;DR: Reranking Transformers as discussed by the authors incorporate both local and global features to rerank the matching images in a supervised fashion and thus replace the relatively expensive process of geometric verification by leveraging operations such as geometric verification based on local features.
Posted Content
When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations
TL;DR: In this paper, a sharpness-aware optimizer was proposed to improve the accuracy and robustness of vision transformers and MLP-mixers on various tasks spanning supervised, adversarial, contrastive, and transfer learning.
Posted Content
BEVT: BERT Pretraining of Video Transformers.
Rui Wang,Dongdong Chen,Zuxuan Wu,Yinpeng Chen,Xiyang Dai,Mengchen Liu,Yu-Gang Jiang,Luowei Zhou,Lu Yuan +8 more
TL;DR: Li et al. as discussed by the authors proposed BEVT, which decouples video representation learning into spatial representation learning and temporal dynamics learning and achieved state-of-the-art performance on three challenging video benchmarks.
Posted Content
A Review of Location Encoding for GeoAI: Methods and Applications.
TL;DR: Location Encoding: Location Encoding as mentioned in this paper is a common need for artificial intelligence models to represent and encode various types of spatial data in a hidden embedding space so that they can be readily incorporated into deep learning models.
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.