SPair-71k

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

Angjoo Kanazawa, Yossi Gandelsman, Norman Mu, David Chan, Jitendra Malik (2024). Dataset: SPair-71k. https://doi.org/10.57702/uv76t6mb

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2003.11657
Citation
  • https://doi.org/10.48550/arXiv.2311.04336
  • https://doi.org/10.48550/arXiv.2311.18540
  • https://doi.org/10.48550/arXiv.2007.10587
  • https://doi.org/10.48550/arXiv.2305.14334
Author Angjoo Kanazawa
More Authors
Yossi Gandelsman
Norman Mu
David Chan
Jitendra Malik
Homepage https://arxiv.org/abs/1908.10543