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
Improved OOD Generalization via Adversarial Training and Pre-training
TL;DR: The authors theoretically show that a model robust to input perturbation generalizes well on out-of-distribution (OOD) data, and empirically verify it on both image classification and natural language understanding tasks.
Posted Content
ATS: Adaptive Token Sampling For Efficient Vision Transformers
Mohsen Fayyaz,Soroush Abbasi Kouhpayegani,Farnoush Rezaei Jafari,Eric Sommerlade,Hamid Reza Vaezi Joze,Hamed Pirsiavash,Juergen Gall +6 more
TL;DR: ATS as discussed by the authors is a differentiable parameter-free adaptive token sampling (ATS) module, which can be plugged into any existing vision transformer architecture and empowers vision transformers by scoring and adaptively sampling significant tokens.
Posted Content
INTERN: A New Learning Paradigm Towards General Vision
Jing Shao,Siyu Chen,Yangguang Li,Kun Wang,Zhenfei Yin,Yinan He,Teng Jianing,Qinghong Sun,Mengya Gao,Jihao Liu,Huang Gengshi,Guanglu Song,Yichao Wu,Yuming Huang,Fenggang Liu,Huan Peng,Shuo Qin,Chengyu Wang,Yujie Wang,Conghui He,Ding Liang,Yu Liu,Fengwei Yu,Junjie Yan,Dahua Lin,Xiaogang Wang,Yu Qiao +26 more
TL;DR: In this paper, a new learning paradigm named INTERN is proposed, which learns with supervisory signals from multiple sources in multiple stages, and the model being trained will develop strong generalizability.
Posted Content
Ice hockey player identification via transformers
TL;DR: In this paper, a transformer network for recognizing players through their jersey numbers in broadcast National Hockey League (NHL) videos is proposed. But, the proposed network performs better than the previous benchmark on the dataset used.
Posted Content
Sequential Random Network for Fine-grained Image Classification.
TL;DR: Zhang et al. as mentioned in this paper proposed a sequence random network (SRN) to enhance the performance of deep convolutional neural network (DCNN) for fine-grained image recognition.
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.