An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-training
Open Access
- 13 February 2025
- journal article
- research article
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (7) , 3918-3950
Abstract
No abstract availableKeywords
This publication has 97 references indexed in Scilit:
- DeiT III: Revenge of the ViT2022
- What to Hide from Your Students: Attention-Guided Masked Image Modeling2022
- Bootstrapped Masked Autoencoders for Vision BERT Pretraining2022
- DisCo: Remedying Self-supervised Learning on Lightweight Models with Distilled Contrastive Learning2022
- Joint Feature Learning and Relation Modeling for Tracking: A One-Stream Framework2022
- FEAR: Fast, Efficient, Accurate and Robust Visual Tracker2022
- Knowledge Distillation Meets Self-supervision2020
- Deep Clustering for Unsupervised Learning of Visual Features2018
- Progressive Neural Architecture Search2018
- Unified Perceptual Parsing for Scene Understanding2018