D2SA

The D2SA dataset is a class-specific amodal segmentation dataset, containing 2000 and 3600 original and artificially augmented images for training and validation.

Data and Resources

Cite this as

Patrick Follmann, Rebecca König, Philipp Härtinger, Michael Klostermann, Tobias Böttger (2024). Dataset: D2SA. https://doi.org/10.57702/2b3el5d8

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.1145/3343031.3350911
Author Patrick Follmann
More Authors
Rebecca König
Philipp Härtinger
Michael Klostermann
Tobias Böttger