Source-Adaptive Discriminative Kernels based Network for Remote Sensing Pansharpening

Authors: Siran Peng, Liang-Jian Deng, Jin-Fan Hu, Yuwei Zhuo

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results indicate that ADKNet outperforms current state-of-the-art (SOTA) pansharpening methods in both quantitative and qualitative assessments, in the meanwhile only with about 60,000 network parameters.
Researcher Affiliation Academia Siran Peng , Liang-Jian Deng , Jin-Fan Hu and Yuwei Zhuo University of Electronic Science and Technology of China, Chengdu, 611731
Pseudocode No No structured pseudocode or algorithm blocks are present in the paper.
Open Source Code Yes The code is available at http://github.com/liangjiandeng/ADKNet.
Open Datasets Yes The dataset is downloaded from the public website2, which contains 12580 samples.
Dataset Splits Yes We process the dataset to PAN/LR-MS/GT image pairs (70%/20%/10% as training/validation/testing dataset) with the size of 64 64, 64 64 8 and 16 16 8 following Wald s protocol by [Wald et al., 1997], same as Fusion Net by [Deng et al., 2021].
Hardware Specification Yes For a fair comparison, all CNN-based approaches are trained on the same Nvidia GPU-2080Ti and Pytorch environments.
Software Dependencies No The paper mentions 'Pytorch environments' but does not specify a version number for PyTorch or any other software components.
Experiment Setup Yes In our ADKNet, we set the initial learning rate, epoch, and batch size as 0.003, 1000, and 32, respectively. Thus, the number of iterations is 2.5 105. In addition, the learning rate is reduced by half every 100 epochs and Adam is used as the optimizer.