CF-ViT: A General Coarse-to-Fine Method for Vision Transformer.

Mengzhao Chen Mingbao Lin Ke Li Yunhang Shen Yongjian Wu Fei Chao Rongrong Ji

Published in: AAAI (2023)

Keyphrases

coarse to fine
hierarchical representation
dynamic programming
neural network
multiscale
pairwise
multiresolution
object detection
collaborative filtering
hierarchical segmentation
machine learning
computer vision
multi view
energy function
optical flow algorithm