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
Proceedings ArticleDOI
Visual-Semantic Transformer for Face Forgery Detection
TL;DR: Zhang et al. as mentioned in this paper proposed a visual-semantic transformer (VST) to detect face forgery based on semantic aware feature relations, which achieved 99.58% accuracy on FF++(Raw) and 96.16% on Celeb-DF.
Proceedings ArticleDOI
Keyword-based Vehicle Retrieval
TL;DR: In this article, a natural language-based vehicle retrieval system is proposed to make controlling a city-scale traffic system easy to maintain and adaptable to changing requirements, which provides a convenient means in managing traffic flows or detecting accidents related to a specific vehicle.
Journal ArticleDOI
Revisiting image captioning via maximum discrepancy competition
TL;DR: A novel method based on maximum discrepancy competition to diagnose existing ICMs and yields several interesting findings, including that using simultaneously low- and high-level object features may be an effective tool to boost the generalization ability for the Transformer based ICMs.
Posted Content
Less is More: Pay Less Attention in Vision Transformers.
TL;DR: Zhang et al. as discussed by the authors used pure multi-layer perceptrons (MLP) to encode rich local patterns in the early stages while applying self-attention modules to capture longer dependencies in deeper layers.
Posted Content
OW-DETR: Open-world Detection Transformer.
TL;DR: In this article, an end-to-end transformer-based framework, OW-DETR, is proposed for open-world object detection, which comprises three dedicated components namely, attention-driven pseudo-labeling, novelty classification and objectness scoring to explicitly address the aforementioned OWOD challenges.
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.