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
Proceedings ArticleDOI
Action Spotting and Temporal Attention Analysis in Soccer Videos
Hiroaki Minoura,Tsubasa Hirakawa,Takayoshi Yamashita,Hironobu Fujiyoshi,Mitsuru Nakazawa,Yeong Nam Chae,Bjorn Stenger +6 more
TL;DR: In this article, the authors used a transformer model to capture important features before and after action scenes, and analyzed which time instances the model focuses on when predicting an action by observing the internal weights of the transformer.
Posted ContentDOI
Sequence-to-Sequence Piano Transcription with Transformers
TL;DR: In this paper, a generic encoder-decoder Transformer with standard decoding methods is used to translate spectrogram inputs directly to MIDI-like output events for several transcription tasks.
Posted Content
Long Short-Term Transformer for Online Action Detection.
TL;DR: In this paper, Long Short-term TRansformer (LSTR) is proposed for online action detection by employing a long and short-term memories mechanism that is able to model prolonged sequence data.
Posted Content
FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
Rui Liu,Hanming Deng,Yangyi Huang,Xiaoyu Shi,Lewei Lu,Wenxiu Sun,Xiaogang Wang,Jifeng Dai,Hongsheng Li +8 more
TL;DR: Fuseformer as discussed by the authors proposes a fine-grained feature fusion based on soft split and soft composition operations for video inpainting, where the soft split divides feature map into many patches with given overlapping interval and the soft composition operates by stitching different patches into a whole feature map.
Posted Content
Channelized Axial Attention for Semantic Segmentation -- Considering Channel Relation within Spatial Attention for Semantic Segmentation.
TL;DR: In this article, the authors proposed Channelized Axial Attention (CAA) to seamlessly integrate channel attention and spatial attention into a single operation with negligible computation overhead, and they further developed grouped vectorization, which allows their model to run with very little memory consumption without slowing down the running speed.
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.