SPair-71k: A large-scale benchmark for semantic correspondence

The proposed method, dubbed Dynamic Hyperpixel Flow, learns to compose hypercolumn features on the fly by selecting a small number of relevant layers from a deep convolutional neural network.

Data and Resources

Cite this as

Juhong Min, Jongmin Lee, Jean Ponce, Minsu Cho (2024). Dataset: SPair-71k: A large-scale benchmark for semantic correspondence. https://doi.org/10.57702/peazps5x

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2007.10587
Author Juhong Min
More Authors
Jongmin Lee
Jean Ponce
Minsu Cho
Homepage https://arxiv.org/abs/1908.10543