Deep Geometric Moment (DGM) Model

The proposed model consists of three components: 1) Coordinate base computation: uses a 2D coordinate grid as input and generates the bases, 2) Image feature computation: obtains image features through ResNet blocks, and 3) Affine transform estimation: to transform the 2D coordinate grid to enable invariance learning.

Data and Resources

Cite this as

Rajhans Singh, Pavan Turaga, Ankita Shukla (2024). Dataset: Deep Geometric Moment (DGM) Model. https://doi.org/10.57702/kptf2pm1

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Author Rajhans Singh
More Authors
Pavan Turaga
Ankita Shukla
Homepage https://arxiv.org/abs/2006.11117