Xiaohua Zhai | VitaVision

Xiaohua Zhai

2 papers · 9 atlas pages

Papers (2)

Source

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Dosovitskiy, Beyer, Kolesnikov, Weissenborn et al. · ICLR 2021 (arXiv 2020) 2020

Source

SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Tschannen, Gritsenko, Wang, Naeem et al. · arXiv preprint 2025

In the Atlas (9)

CLIP DeiT DINOv2 MAE Positional Encoding RF-DETR SegFormer Transformer ViT

Co-authors (23)

Lucas Beyer2 shared papers
Ibrahim Alabdulmohsin1 shared paper
Mostafa Dehghani1 shared paper
Alexey Dosovitskiy1 shared paper
Talfan Evans1 shared paper
Sylvain Gelly1 shared paper
Alexey A. Gritsenko1 shared paper
Jeremiah Harmsen1 shared paper
Georg Heigold1 shared paper
Olivier J. Hénaff1 shared paper
Neil Houlsby1 shared paper
Alexander Kolesnikov1 shared paper
Matthias Minderer1 shared paper
Basil Mustafa1 shared paper
Muhammad Ferjad Naeem1 shared paper
Nikhil Parthasarathy1 shared paper
Andreas Steiner1 shared paper
Michael Tschannen1 shared paper
Thomas Unterthiner1 shared paper
Jakob Uszkoreit1 shared paper
Xiao Wang1 shared paper
Dirk Weissenborn1 shared paper
Ye Xia1 shared paper