Pre-training Vision Transformers with Very Limited Synthesized Images

27 July 2023

Papers citing "Pre-training Vision Transformers with Very Limited Synthesized Images"

9 / 9 papers shown

Title
MoireDB: Formula-generated Interference-fringe Image Dataset Yuto Matsuo Ryo Hayamizu Hirokatsu Kataoka Akio Nakamura 37 0 0 03 Feb 2025
Data Collection-free Masked Video Modeling Yuchi Ishikawa Masayoshi Kondo Yoshimitsu Aoki ViT 19 1 0 10 Sep 2024
Scaling Backwards: Minimal Synthetic Pre-training? Ryo Nakamura Ryu Tadokoro Ryosuke Yamada Tim Puhlfürß Iro Laina Christian Rupprecht Walid Maalej Rio Yokota Hirokatsu Kataoka DD 22 2 0 01 Aug 2024
Reinforcement Learning with Generative Models for Compact Support Sets Nico Schiavone Xingyu Li 16 0 0 25 Apr 2024
Training Vision Transformers with Only 2040 Images Yunhao Cao Hao Yu Jianxin Wu ViT 110 42 0 26 Jan 2022
Masked Autoencoders Are Scalable Vision Learners Kaiming He Xinlei Chen Saining Xie Yanghao Li Piotr Dollár Ross B. Girshick ViT TPM 305 7,434 0 11 Nov 2021
Improving Fractal Pre-training Connor Anderson Ryan Farrell 88 27 0 06 Oct 2021
Emerging Properties in Self-Supervised Vision Transformers Mathilde Caron Hugo Touvron Ishan Misra Hervé Jégou Julien Mairal Piotr Bojanowski Armand Joulin 317 5,775 0 29 Apr 2021
Pre-training without Natural Images Hirokatsu Kataoka Kazushige Okayasu Asato Matsumoto Eisuke Yamagata Ryosuke Yamada Nakamasa Inoue Akio Nakamura Y. Satoh 79 116 0 21 Jan 2021