Deep Regression Representation Learning with Topology
Authors: Shihao Zhang, Kenji Kawaguchi, Angela Yao
ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on synthetic and real-world regression tasks demonstrate the benefits of PH-Reg. |
| Researcher Affiliation | Academia | Shihao Zhang 1 Kenji Kawaguchi 1 Angela Yao 1 1National Unviersity of Singapore. Correspondence to: Shihao Zhang <zhang.shihao@u.nus.edu>. |
| Pseudocode | No | The paper describes its methods using mathematical formulas and textual explanations, but it does not include any clearly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | Code: https: //github.com/needylove/PH-Reg. |
| Open Datasets | Yes | We randomly sample 3000 points with coordinate y R3 from each object. These 3000 points are then divided into sets of 100 for training, 100 for validation, and 2800 for testing. ... We exploit the Age DB-DIR (Yang et al., 2021) for age estimation task. ... We use the DIV2K dataset (Timofte et al., 2017) for 4x super-resolution training... We exploit the NYU-Depth-v2 (Silberman et al., 2012) for the depth estimation task. |
| Dataset Splits | Yes | These 3000 points are then divided into sets of 100 for training, 100 for validation, and 2800 for testing. ... We evaluate on the validation set of DIV2K and the standard benchmarks: Set5 (Bevilacqua et al., 2012), Set14 (Zeyde et al., 2012), BSD100 (Martin et al., 2001), Urban100 (Huang et al., 2015). |
| Hardware Specification | No | The paper mentions 'Memory (MB)' in Table 5 to quantify memory usage but does not provide specific details such as GPU or CPU models, or other hardware specifications used for running the experiments. |
| Software Dependencies | No | The paper does not list specific software dependencies with version numbers (e.g., 'PyTorch 1.9' or 'Python 3.8') that would be required for replication. |
| Experiment Setup | Yes | We train the models for 10000 epochs using Adam W as the optimizer with a learning rate of 0.001. ... The trade-off parameters λd and λt are default set to 10 and 100, respectively, while λt is set to 10000 and λd is set to 1 for Mammoth, and λd is set to 1 for torus and circle. |