PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs

Authors: Zhengyang Shen, Tiancheng Shen, Zhouchen Lin, Jinwen Ma9585-9593

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In Experiments, PDO-e S2CNNs show greater parameter efficiency and outperform other spherical CNNs significantly on several tasks.
Researcher Affiliation Academia 1 School of Mathematical Sciences and LMAM, Peking University 2 Center for Data Science, Peking University 3 The Chinese University of Hong Kong 4 Key Lab. of Machine Perception (Mo E), School of EECS, Peking University 5 Pazhou Lab, Guangzhou, China
Pseudocode No The paper describes the method mathematically and textually but does not provide structured pseudocode or an algorithm block.
Open Source Code No The paper does not contain an explicit statement offering the source code for the described methodology, nor does it provide a link to a code repository.
Open Datasets Yes Spherical MNIST Classification We follow (Cohen et al. 2018) in the preparation of the spherical MNIST... and We evaluate our method on the Stanford 2D-3D-S dataset (Armeni et al. 2017)... and Finally, we apply our method to the QM7 dataset (Blum and Reymond 2009; Rupp et al. 2012)...
Dataset Splits Yes We randomly select 6,000 training images as a validation set, and choose the model with the lowest validation error during training. and We use the official 3-fold cross validation to train and evaluate our model and We use the official 5-fold cross validation to train and evaluate our model
Hardware Specification No The paper does not explicitly describe the specific hardware used to run its experiments, such as GPU or CPU models.
Software Dependencies No The paper does not specify any software dependencies with version numbers, such as programming languages, libraries, or frameworks.
Experiment Setup No The data preprocessing, model architectures and training details for each task are provided in the Supplementary Material for reproducing our results.