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
Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation.
TL;DR: Wang et al. as mentioned in this paper proposed a pure transformer-based U-shaped Encoder-Decoder architecture with skip-connections for local-global semantic feature learning for medical image segmentation.
Posted Content
Video Swin Transformer.
TL;DR: In this article, the authors advocate an inductive bias of locality in video Transformers, which leads to a better speed-accuracy trade-off compared to previous approaches which compute self-attention globally even with spatial-temporal factorization.
Posted Content
Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth
TL;DR: The authors showed that self-attention networks can be decomposed into a sum of smaller terms, each involving the operation of a sequence of attention heads across layers, and showed that without skip connections or multi-layer perceptrons (MLPs), the output converges doubly exponentially to a rank-1 matrix.
Posted Content
Residual Attention: A Simple but Effective Method for Multi-Label Recognition
Ke Zhu,Jianxin Wu +1 more
TL;DR: In this paper, a simple module named class-specific residual attention (CSRA) is proposed to capture different spatial regions occupied by objects from different categories, which leads to consistent improvement across many diverse pretrained models and datasets.
Posted Content
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
TL;DR: DAformer as mentioned in this paper proposes a Transformer encoder and a multi-level context-aware feature fusion decoder for unsupervised domain adaptation (UDA), which is enabled by three crucial training strategies to stabilize the training and avoid overfitting.
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.