Stand-Alone Self-Attention in Vision Models - NeurIPS-2019-stand-alone-self-attention-in-vision-models-Paper.pdf
papers.nips.cc · 6,848 words · saved by 1 readers
N/A
Stand-Alone Self-Attention in Vision Models Prajit Ramachandran∗ Niki Parmar∗ Ashish Vaswani∗ Irwan Bello Anselm Levskaya† Jonathon Shlens Google Research, Brain Team {prajit, nikip, avaswani}@google.com Abstract Convolutions are a fundamental building block of modern computer vision systems. Recent approaches have argued for going beyond convolutions in…
saved by
related reading
- transformer_attention.pdfarxiv.org
- The Annotated Transformernlp.seas.harvard.edu
- Learning Unsupervised Visual Grounding Through Semantic Self-Supervisionijcai.org
- d89a66c7c80a29b1bdbab0f2a1a94af8-Paper.pdfproceedings.neurips.cc
- 1706.03762arxiv.org
- Attention is All you Needproceedings.neurips.cc
- [2203.09795] Three things everyone should know about Vision Transformersarxiv.org
- Feature Visualizationdistill.pub
- An Analysis of Scale Invariance in Object Detection SNIP - Singh_An_Analysis_of_CVPR_2018_paper.pdfopenaccess.thecvf.com
- Locally Scale-Invariant Convolutional NeuralNetworksarxiv.org
- Learning 3D object-centric representation through predictionarxiv.org
- ImageNet Classification with Deep Convolutional Neural Networksproceedings.neurips.cc