Sense Beauty by Label Distribution Learning
Authors: Yi Ren, Xin Geng
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Section 4 Experiments: We do the experiment on the M2B dataset, and set λ to 20. To prove the accuracy, BDT algorithm is compared with the conventional pairwise ranking method Ranking SVM following the settings in [Nguyen et al., 2012]. We measure the performance by comparing the results with the pairwise preferences obtained from k-wise comparisons. |
| Researcher Affiliation | Academia | Yi Ren, Xin Geng MOE Key Laboratory of Computer Network and Information Integration, School of computer Science and Engineering, Southeast University, Nanjing, China {y.ren, xgeng}@seu.edu.cn |
| Pseudocode | Yes | Algorithm 1 Structural Label Distribution Learning(SLDL) |
| Open Source Code | No | The paper does not provide any explicit statements or links indicating that the source code for the described methodology (BDT or SLDL) is publicly available. |
| Open Datasets | Yes | In the experiments, we use the SCUT-FBP dataset[Xie et al., 2015] and the Multi-Modality Beauty (M2B) dataset [Nguyen et al., 2012], which are just fit to the two conditions mentioned before, the former contains the whole ratings of each image, and the latter contains the k-wise comparisons. |
| Dataset Splits | Yes | Ten-fold cross validation is conducted. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used to run the experiments (e.g., CPU, GPU models, memory specifications). |
| Software Dependencies | No | The paper mentions using "BFGS" as an optimization algorithm and specific feature descriptors like "LBP", "HOG", and "Gabor filter". It also mentions "SVR" and "k-NN" as baseline methods. However, it does not provide specific version numbers for any software libraries, frameworks, or solvers used (e.g., Python version, TensorFlow/PyTorch version, specific library versions for SVR or k-NN). |
| Experiment Setup | Yes | The regularization parameter in simplified DFAT network is set to 0.005. SVR is set with a linear kernel. The k in k-NN is set to 1, and the distance is computed by the Euclidean distance. SLDL is set with a linear kernel and C is 400. We do the experiment on the M2B dataset, and set λ to 20. The features of the images are extracted by three popular descriptors, i.e., LPB [Ojala et al., 2002] with a cell size of 64 × 64 pixels; HOG [Dalal and Triggs, 2005] with a cell size of 32 × 32 pixels; Gabor filter [Jain and Farrokhnia, 1991] with 2 scales and 4 orientations. Since the features we extracted are high-dimensional, we use PCA to reduce the dimensionality to 300. |