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
AniFormer: Data-driven 3D Animation with Transformer.
TL;DR: Aniformer as discussed by the authors generates animated 3D sequences by directly taking the raw driving sequences and arbitrary same-type target meshes as inputs, integrating styles from target meshes and motions from the driving meshes.
Posted Content
Towards High-Quality Temporal Action Detection with Sparse Proposals.
TL;DR: SP-TAD as discussed by the authors introduces sparse proposals to interact with the hierarchical features to localize the temporal segments containing human action instances and predict the action categories, which enables utilization of high-resolution features to preserve action instances details.
Posted Content
Motion Planning Transformers: One Model to Plan Them All
TL;DR: In this article, a transformer-based approach is proposed to solve the complex motion planning problems in the real world, where the transformers are used to identify regions on the map using transformers to provide attention to map areas likely to include the best path and then apply local planners to generate the final collision-free path.
Posted Content
Visual Parser: Representing Part-whole Hierarchies with Transformers.
TL;DR: Zhang et al. as discussed by the authors propose Visual Parser (ViP) which divides visual representations into two levels, the part level and the whole level, and encode the information from the whole into part vectors through an attention mechanism, then decode the global information within the part vectors back into the whole representation.
Posted Content
Searching for Efficient Multi-Stage Vision Transformers
TL;DR: Zhang et al. as discussed by the authors proposed an efficient multi-stage ViT architecture designed with neural architecture search (NAS), where residual spatial reduction was used to decrease sequence lengths for deeper layers.
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.