Search Results for author:
Found 4 papers, 2 papers with code
OpenIncrement: A Unified Framework for Open Set Recognition and Deep Class-Incremental Learning
In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining.
GCNH: A Simple Method For Representation Learning On Heterophilous Graphs
Yet, achievement of consistent GNN performance on heterophilous graphs remains an open research problem.
Ranked #7 on
Node Classification
on Cornell
Node Classification on Non-Homophilic (Heterophilic) Graphs
Representation Learning
2-hop Neighbor Class Similarity (2NCS): A graph structural metric indicative of graph neural network performance
In this work, we highlight the limitations of the widely used homophily ratio and the recent Cross-Class Neighborhood Similarity (CCNS) metric in estimating GNN performance.
A Conditional Generative Adversarial Network to Fuse Sar And Multispectral Optical Data For Cloud Removal From Sentinel-2 Images
In this paper, we present the first conditional generative adversarial network (cGAN) architecture that is specifically designed to fuse synthetic aperture radar (SAR) and optical multi-spectral (MS) image data to generate cloud- and haze-free MS optical data from a cloud-corrupted MS input and an auxiliary SAR image.
Ranked #5 on
Cloud Removal
on SEN12MS-CR
