Unsupervised Co-part Segmentation through Assembly
Authors: Qingzhe Gao, Bin Wang, Libin Liu, Baoquan Chen
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We demonstrate the effectiveness of our approach with a host of extensive experiments, ranging from human bodies, hands, quadruped, and robot arms. We show that our approach can achieve meaningful and compact part segmentation, outperforming state-of-the-art approaches on diverse benchmarks. |
| Researcher Affiliation | Academia | 1Shandong University, Qingdao, Shandong, China 2AICFVE, Beijing Film Academy, Beijing, China 3CFCS, Peking University, Beijing, China. |
| Pseudocode | No | The paper describes the network architecture and training process using text and diagrams, but does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not contain any statement about releasing code or a link to a code repository. |
| Open Datasets | Yes | Tai-Chi-HD dataset (Siarohin et al., 2019) ... The Vox Celeb dataset (Nagrani et al., 2017) ... Exercise dataset ... originally collected by (Xue et al., 2016) ... provided by (Xu et al., 2019) |
| Dataset Splits | No | The paper mentions 'validation set' in table captions (e.g., Table 1, Table 2) but does not provide specific details on how the validation splits were created (e.g., percentages or exact counts) within the text describing the datasets, nor for reproducibility. |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware (e.g., GPU models, CPU types) used for running the experiments. |
| Software Dependencies | No | The paper mentions using a 'standard U-Net architecture' and 'a pretrained VGG-19 network'. However, it does not provide specific version numbers for these or any other software dependencies, which are necessary for reproducible descriptions. |
| Experiment Setup | No | We include the details about the network structure and the training settings in the supplementary materials. The main text does not contain specific hyperparameters or training configurations. |