Search Results for author:
Found 2 papers, 2 papers with code
Pushing the Limits of Capsule Networks
Convolutional neural networks use pooling and other downscaling operations to maintain translational invariance for detection of features, but in their architecture they do not explicitly maintain a representation of the locations of the features relative to each other.
Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation
We design a simple but surprisingly effective visual recognition benchmark for studying bias mitigation.
Ranked #1 on
Out-of-Distribution Generalization
on UrbanCars
Cannot find the paper you are looking for? You can
Submit a new open access paper.
