You're currently viewing an old version of this dataset. To see the current version, click here.

PASCAL-5i

Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps from the frozen visual encoder to compute the pixel-wise similarity as a key prior guidance for the decoder.

Data and Resources

Cite this as

Siddhartha Gairola, Mayur Hemani, Ayush Chopra, Balaji Krishnamurthy (2024). Dataset: PASCAL-5i. https://doi.org/10.57702/nt3ivyfn

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.2004.02945
Citation
  • https://doi.org/10.48550/arXiv.2004.15014
  • https://doi.org/10.48550/arXiv.2306.15278
  • https://doi.org/10.48550/arXiv.2405.08458
  • https://doi.org/10.48550/arXiv.2009.06680
  • https://doi.org/10.1016/j.patcog.2022.109018
  • https://doi.org/10.48550/arXiv.2202.06498
Author Siddhartha Gairola
More Authors
Mayur Hemani
Ayush Chopra
Balaji Krishnamurthy
Homepage https://www.pascal-5i.org/