Relational Knowledge Transfer for Zero-Shot Learning

Authors: Donghui Wang, Yanan Li, Yuetan Lin, Yueting Zhuang

AAAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on three challenging datasets show prominent performance obtained by RKT, and we obtain 82.43% accuracy on the Animals with Attributes dataset.
Researcher Affiliation Academia Donghui Wang, Yanan Li, Yuetan Lin, Yueting Zhuang College of Computer Science, Zhejiang University, Hangzhou, China {dhwang, ynli, linyuetan, yzhuang}@zju.edu.cn
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link regarding the availability of source code for the methodology described.
Open Datasets Yes We evaluate our work on three real-world ZSL datasets: Animals with Attributes (Aw A) (Lampert, Nickisch, and Harmeling 2009), Caltech UCSD Birds (CUB) (Wah et al. 2011) and Stanford Dogs (Dogs) (Khosla et al. 2011).
Dataset Splits No The paper mentions 'training dataset' and 'testing label space' but does not specify exact training, validation, and test splits (e.g., percentages or sample counts) for reproducibility, nor does it explicitly mention a validation set.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory, or cloud computing instance types) used for running experiments.
Software Dependencies No The paper mentions using VGG, Goog Le Net, and Word2Vec, but does not provide specific version numbers for any software dependencies or libraries.
Experiment Setup No The paper mentions adjusting parameters like λ in sparse coding and the number of instances per class (NPC), but it lacks specific details on typical experimental setup hyperparameters such as learning rates, batch sizes, optimizers, or number of training epochs.