Search Results for author:
Found 3 papers, 1 papers with code
On Pitfalls of $\textit{RemOve-And-Retrain}$: Data Processing Inequality Perspective
Approaches for appraising feature importance approximations, alternatively referred to as attribution methods, have been established across an extensive array of contexts.
A Billion-scale Foundation Model for Remote Sensing Images
Recently, research in the remote sensing field has focused primarily on the pretraining method and the size of the dataset, with limited emphasis on the number of model parameters.
Ranked #1 on
Semantic Segmentation
on LoveDA
(using extra training data)
Contrastive Multiview Coding with Electro-optics for SAR Semantic Segmentation
In the training of deep learning models, how the model parameters are initialized greatly affects the model performance, sample efficiency, and convergence speed.
