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
GraphiT: Encoding Graph Structure in Transformers
TL;DR: GraphiT as discussed by the authors uses relative positional encoding strategies in self-attention scores based on positive definite kernels on graphs and enumerating and encoding local sub-structures such as paths of short length.
Posted Content
MASS: Multi-Attentional Semantic Segmentation of LiDAR Data for Dense Top-View Understanding.
Kunyu Peng,Juncong Fei,Kailun Yang,Alina Roitberg,Jiaming Zhang,Frank Bieder,Philipp Heidenreich,Christoph Stiller,Rainer Stiefelhagen +8 more
TL;DR: In this paper, a multi-attentional semantic segmentation model for dense top-view understanding of the driving scenes is proposed, which operates on pillar and occupancy features and comprises three attention-based building blocks: (1) a keypoint-driven graph attention, (2) an LSTM-based attention computed from a vector embedding of the spatial input, and (3) a pillar-based Attention, resulting in a dense 360-degree segmentation mask.
Long-context Transformers: A survey
TL;DR: In this article, the authors considered the most up-to-date methods and how these methods compare to each other in different tasks and addressed their limitations and how well they perform, and which ones are most versatile and could be used as a base for future works.
Posted Content
Transferability Metrics for Selecting Source Model Ensembles
TL;DR: In this article, the authors propose several transferability metrics designed for this task and evaluate them in a challenging and realistic transfer learning setup for semantic segmentation, and compare the ensemble selected by their method to two baselines which select a single source model, either (1) from the same pool as their method; or (2) from a pool containing large source models, each with similar capacity as an ensemble.
Posted Content
Transformer-Based Source-Free Domain Adaptation
TL;DR: TransDA as discussed by the authors applies the Transformer as the attention module and injects it into a convolutional network to encourage the model to turn attention towards the object regions, which can effectively improve the model's generalization ability on the target domains.
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.