Regularizing self-attention on vision transformers with 2D spatial distance loss
- 18 July 2022
- journal article
- research article
- Published by Springer Nature in Artificial Life and Robotics
- Vol. 27 (3) , 586-593
Abstract
No abstract availableKeywords
This publication has 15 references indexed in Scilit:
- A Survey on Vision TransformerIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference2021
- Visformer: The Vision-friendly Transformer2021
- Emerging Properties in Self-Supervised Vision Transformers2021
- Conformer: Local Features Coupling Global Representations for Visual Recognition2021
- Exploring Self-Attention for Image Recognition2020
- Revisiting Unreasonable Effectiveness of Data in Deep Learning Era2017
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- ImageNet: A large-scale hierarchical image database2009
- Automated Flower Classification over a Large Number of Classes2008