Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
SageMix: Saliency-Guided Mixup for Point Clouds
Authors: Sanghyeok Lee, Minkyu Jeon, Injae Kim, Yunyang Xiong, Hyunwoo J. Kim
NeurIPS 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate that the proposed method consistently outperforms existing Mixup methods in various benchmark point cloud datasets. 4 Experiments In this section, we demonstrate the effectiveness of our proposed method Sage Mix with various benchmark datasets. |
| Researcher Affiliation | Collaboration | Sanghyeok Lee Korea University EMAIL Minkyu Jeon Korea University EMAIL Injae Kim Korea University EMAIL Yunyang Xiong Meta Reality Labs EMAIL Hyunwoo J. Kim Korea University EMAIL |
| Pseudocode | Yes | The overall pipeline is illustrated in Figure 2 and pseudocode is provided in Algorithm 1 . Algorithm 1 A saliency-guided Mixup for point clouds |
| Open Source Code | Yes | Code is available at https://github.com/mlvlab/Sage Mix. |
| Open Datasets | Yes | We use two benchmark dataset: 3D Warehouse dataset (MN40) [18] and Scan Object NN [19]. |
| Dataset Splits | Yes | MN40 is a synthetic dataset containing 9,843 CAD models for training and 2,468 CAD models for evaluation. Scan Object NN... is a real-world dataset that is split into 80% for training and 20% for evaluation. |
| Hardware Specification | No | The paper states 'National Supercomputing Center with supercomputing resources including technical support (KSC-2022-CRE-0261)' in the acknowledgments, but does not provide specific hardware details like GPU or CPU models in the main text. |
| Software Dependencies | No | The paper does not explicitly provide specific software dependencies with version numbers (e.g., 'PyTorch 1.9', 'Python 3.8'). |
| Experiment Setup | No | Implementation details are provided in Appendix A. (However, Appendix A itself is not provided in the input text, thus specific values are not present in the given context). |