General Heterogeneous Transfer Distance Metric Learning via Knowledge Fragments Transfer
Authors: Yong Luo, Yonggang Wen, Tongliang Liu, Dacheng Tao
IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on both scene classification and object recognition demonstrate superiority of the proposed method.In this section, we evaluate the effectiveness of the proposed HTDML algorithm on both scene classification and object recognition. Prior to these evaluations, we present our experimental settings. |
| Researcher Affiliation | Collaboration | School of Computer Science and Engineering, Nanyang Technological University, Singapore UBTech Sydney AI Institute and SIT, FEIT, The University of Sydney, Australia |
| Pseudocode | No | The paper refers to an algorithm from an external source ([Lin, 2007], Algorithm 4) but does not provide its own pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any explicit statements about the release of source code or links to a code repository for the methodology described. |
| Open Datasets | Yes | The dataset used in scene categorization is the Scene-15 [Lazebnik et al., 2006], which contains 4585 images belonging to 15 natural scene categories.We further verify the proposed method in object recognition on a natural image dataset NUS-WIDE (NUS) [Chua et al., 2009]. |
| Dataset Splits | No | We randomly split the image set into a training and test set of equal size.Half of the images are used for training and the rest for test.The paper specifies training and test splits but does not mention a separate validation split. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU or CPU models, memory, or cloud instance types used for running experiments. |
| Software Dependencies | No | The paper mentions algorithms like Gradient Boosting Regression Tree (GBRT) and GB-LMNN but does not specify any software packages or libraries with version numbers used for implementation. |
| Experiment Setup | Yes | The hyper-parameter γ is optimized over the set {10i|i = 5, 4, . . . , 3, 4}.The number of attracted target neighbors is chosen from 1 to 10.The trade-off hyper-parameter is tuned over the set {10i|i = 5, 4, . . . , 3, 4}.σ is set as 0.5 in this paper. |