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
ZS-SLR: Zero-Shot Sign Language Recognition from RGB-D Videos
TL;DR: Zhang et al. as mentioned in this paper proposed a two-stream model from RGB and depth videos for zero-shot sign language recognition (ZS-SLR) and achieved state-of-the-art performance.
Posted Content
Understanding and Improving Robustness of Vision Transformers through Patch-based Negative Augmentation
TL;DR: In this paper, the authors investigate the robustness of vision transformers through the lens of their special patch-based architectural structure, i.e., they process an image as a sequence of image patches.
Posted Content
DAIR: Disentangled Attention Intrinsic Regularization for Safe and Efficient Bimanual Manipulation.
TL;DR: In this article, the authors propose disentangled attention, which provides an intrinsic regularization for two robots to focus on separate sub-tasks and objects, which leads to significantly more efficient and safer cooperative strategies than all the baselines.
Posted Content
ABC: Attention with Bounded-memory Control.
Hao Peng,Jungo Kasai,Nikolaos Pappas,Dani Yogatama,Zhaofeng Wu,Lingpeng Kong,Roy Schwartz,Noah A. Smith +7 more
TL;DR: This paper proposed Attention with bounded-memory control (ABC) to improve the efficiency of the attention mechanism in transformers by reducing the overhead of reading from the attention context, which can be seen as a random access memory with each token taking a slot.
Posted Content
T6D-Direct: Transformers for Multi-Object 6D Pose Direct Regression.
TL;DR: T6D-Direct as discussed by the authors proposes a real-time single-stage direct method with a transformer-based architecture built on DETR to perform 6D multi-object pose direct estimation.
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.