Deep Latent Graph Matching
Authors: Tianshu Yu, Runzhong Wang, Junchi Yan, Baoxin Li
ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiments on datasets including Pascal VOC with Berkeley annotation (Everingham et al., 2010; Bourdev & Malik, 2009), Willow Object Class (Cho et al., 2013) and SPair-71K (Min et al., 2019). We report the per-category and average performance. |
| Researcher Affiliation | Academia | 1Arizona State University 2Shanghai Jiao Tong University. |
| Pseudocode | Yes | Algorithm 1 DLGM-D |
| Open Source Code | No | The paper does not contain an explicit statement about releasing source code or a link to a code repository for the described methodology. |
| Open Datasets | Yes | We conduct experiments on datasets including Pascal VOC with Berkeley annotation (Everingham et al., 2010; Bourdev & Malik, 2009), Willow Object Class (Cho et al., 2013) and SPair-71K (Min et al., 2019). |
| Dataset Splits | Yes | It consists of 70,958 image pairs collected from Pascal VOC 2012 and Pascal 3D+ (53,340 for training, 5,384 for validation and 12,234 for testing). |
| Hardware Specification | No | The paper mentions 'training time' and 'time cost' but does not specify any particular hardware like GPU models, CPU models, or memory. |
| Software Dependencies | No | The paper mentions software components like 'VGG16', 'Spline CNN', 'GCN', and 'Blackbox GM solver' with citations, but does not specify version numbers for these or other ancillary software components used in their implementation. |
| Experiment Setup | Yes | Except for the ablation study, we consistently conduct experiments under α = 5.0 and β = 0.3. |