Neural ePDOs: Spatially Adaptive Equivariant Partial Differential Operator Based Networks

Authors: Lingshen He, Yuxuan Chen, Zhengyang Shen, Yibo Yang, Zhouchen Lin

ICLR 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In experiments, we show that our method can significantly improve previous works with smaller model size in various datasets. Especially, we achieve the state-of-the-art performance on the MNIST-rot dataset with only tenth of parameters of the previous best model.
Researcher Affiliation Collaboration Lingshen He1, Yuxuan Chen2 , Zhengyang Shen3, Yibo Yang2, Zhouchen Lin1,4,5 1 National Key Lab of General AI, School of Intelligence Science and Technology, Peking University 2 JD Explore Academy, Beijing, China 3 Department of Computer Vision Technology (VIS), Baidu Inc. 4 Institute for Artificial Intelligence, Peking University 5 Peng Cheng Laboratory
Pseudocode No The paper describes the proposed methods and their implementation but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement or link for the availability of open-source code for the described methodology.
Open Datasets Yes We first test our model on MNIST-rot dataset (Larochelle et al., 2007), which is a standard benchmark to test the equivariant models. The dataset contains 62k 28 28 randomly rotated gray-scale handwritten digits. Image Net (Deng et al., 2009) is a large-scale dataset that consists of 1000 classes with roughly 1000 images per class, which is a common benchmark for image recognition.
Dataset Splits Yes It contains 1.2 million training images and 50k validation images.
Hardware Specification No The paper does not provide specific hardware details such as GPU or CPU models, memory, or cloud instance types used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No More details about the model, training and hyperparameters analysis can be found in the supplementary material. More detailed training settings can be found in the supplementary material.