Swelling-ViT: Rethink Data-Efficient Vision Transformer from Locality
- 7 November 2024
- book chapter
- Published by Springer Nature
- p. 32-46
Abstract
No abstract availableKeywords
This publication has 15 references indexed in Scilit:
- LKC-Net: large kernel convolution object detection networkScientific Reports, 2023
- Improving Vision Transformers to Learn Small-Size Dataset From ScratchIEEE Access, 2022
- DeiT III: Revenge of the ViT2022
- Training Vision Transformers with only 2040 Images2022
- A ConvNet for the 2020s2022
- Masked Autoencoders Are Scalable Vision Learners2022
- Scaling Up Your Kernels to 31×31: Revisiting Large Kernel Design in CNNs2022
- Scaling Local Self-Attention for Parameter Efficient Visual Backbones2021
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009