Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection

Two-stage object detectors generate object proposals and classify them to detect objects in images. The proposals do not contain the objects perfectly but overlap with them in many possible ways, exhibiting great variability in the difficult levels of the proposals.

Data and Resources

Cite this as

Jingyi Xu, Hieu Le, Dimitris Samaras (2024). Dataset: Generating Features with Increased Crop-related Diversity for Few-Shot Object Detection. https://doi.org/10.57702/8kel6p9i

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Jingyi Xu
More Authors
Hieu Le
Dimitris Samaras