Login / Signup
BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers.
Zhiliang Peng
Li Dong
Hangbo Bao
Qixiang Ye
Furu Wei
Published in:
CoRR (2022)
Keyphrases
</>
vector quantized
image data
vector quantization
input image
progressive transmission
image features
test images
image classification
visual features
multiscale
image segmentation
image compression
similarity measure
optical flow
keypoints
visual words
face recognition