Search Results for author:
Found 2 papers, 1 papers with code
Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNets
Ultimately, we reveal that DSC-based architectures such as MobileNets implicitly rely on cross-kernel correlations, while our BSConv formulation is based on intra-kernel correlations and thus allows for a more efficient separation of regular convolutions.
Ranked #17 on
Fine-Grained Image Classification
on Stanford Dogs
Instance-weighted Transfer Learning of Active Appearance Models
Therefore, we present a transfer learning method that is able to learn from related training data using an instance-weighted transfer technique.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
