1 code implementation • 5 Oct 2023 • Jiawen Xu, Claas Grohnfeldt, Odej Kao
In most works on deep incremental learning research, it is assumed that novel samples are pre-identified for neural network retraining.
1 code implementation • 21 Apr 2023 • Andrea Cavallo, Claas Grohnfeldt, Michele Russo, Giulio Lovisotto, Luca Vassio
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
no code implementations • 26 Dec 2022 • Andrea Cavallo, Claas Grohnfeldt, Michele Russo, Giulio Lovisotto, Luca Vassio
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.
no code implementations • IGARSS 2018 • Claas Grohnfeldt, Michael Schmitt, Xiaoxiang Zhu
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