Graph and Autoencoder Based Feature Extraction for Zero-shot Learning
Authors: Yang Liu, Deyan Xie, Quanxue Gao, Jungong Han, Shujian Wang, Xinbo Gao
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on five attribute datasets demonstrate the effectiveness of the proposed model. and We perform experiments on five popular datasets and excellent results demonstrate the effectiveness of the proposed model. |
| Researcher Affiliation | Academia | 1 State Key Laboratory of Integrated Services Networks, Xidian University, Xi an 710071, China 2 WMG Data Science, University of Warwick, CV4 7AL Coventry, United Kingdom 3 School of Electronic Engineering, Xidian University, Xi an 710071, China |
| Pseudocode | Yes | Algorithm 1 : ADMM algorithm for GAFE |
| Open Source Code | No | The paper does not include an unambiguous statement where the authors release their code or provide a direct link to a source-code repository. |
| Open Datasets | Yes | SUN Attribute (SUN) [Patterson et al., 2014] is a finegrained dataset... CUB-200-2011 Birds (CUB) [Welinder et al., 2010] is a fine-grained dataset... Animals with Attributes 1 (AWA1) [Lampert et al., 2014] is a coarse-grained dataset... Animals with Attributes 2 (AWA2) [Xian et al., 2018] consists of... A Pascal and Yahoo (a PY) [Farhadi et al., 2009] is a small scale coarse-grained dataset... |
| Dataset Splits | Yes | According to [Lampert et al., 2014], 645 classes are used for training and others for testing. (SUN) Following [Welinder et al., 2010], the training and testing classes are 150 and 50 respectively. (CUB) The number of seen and unseen classes are 40 and 10 respectively. (AWA1) Similarly, 40/10 classes are used for training/testing and all of the 50 categories are the same as AWA1 dataset. (AWA2) in which 20 classes are used for training and 12 others for testing. (a PY) |
| Hardware Specification | No | The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments. |
| Software Dependencies | No | The paper only mentions 'Res Net [He et al., 2016]' without providing specific version numbers for any software dependencies used for implementation or experiments. |
| Experiment Setup | Yes | Our proposed model has two free parameters: α and β (see Eq. (1)). Figure 2 shows the variation of the best results for these two parameters over a small range. From the parameter analysis on α (see Figure 2 (a)), our GAFE achieves the best result when α = 1.4 on the AWA2 dataset while the value of α approaches one on other four datasets. From the parameter analysis on β (see Figure 2 (b)), our GAFE achieves the best result when β = 1 on a PY and AWA2 datasets while the value of β approaches three other three datasets. Empirically, α can be set to 1 < α < 1.4, while β varies from 1 to 3. and Parameter: µmax = 106, ρ = 1.1, ε = 10 3, α and β |