Hyperbolic Knowledge Transfer with Class Hierarchy for Few-Shot Learning

Authors: Baoquan Zhang, Hao Jiang, Shanshan Feng, Xutao Li, Yunming Ye, Rui Ye

IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on three datasets show our method achieves superior performance over state-of-the-art methods, especially on 1-shot tasks.
Researcher Affiliation Academia Harbin Institute of Technology, Shenzhen
Pseudocode No The paper describes the steps of the method in prose but does not include a clearly labeled pseudocode or algorithm block.
Open Source Code No The paper does not include any statement about releasing source code or provide a link to a code repository.
Open Datasets Yes mini Imagenet. This is a subset of the Image Net, which contains 100 classes and 600 images per class. ... tiered Imagenet. This dataset is also derived from the Image Net dataset. ... CIFAR-FS. This dataset is constructed from CIFAR100
Dataset Splits Yes Following the setting of [Peng et al., 2019], we split the data set into 64 classes for training, 16 classes for validation, and 20 classes for test, respectively.
Hardware Specification No The paper mentions using 'Res Net12 as our backbone' but does not specify any hardware details such as GPU models, CPU types, or memory.
Software Dependencies No The paper mentions 'Riemannian Adam optimizer' and 'Res Net12' but does not specify any software versions for libraries, frameworks, or programming languages.
Experiment Setup Yes These hyper-parameters, γ = 1/640, α = 2, β = 1 are used in our all experiments. For hyper-parameters λc and λr, λc = 1 and λr = 2 are used for mini Imagenet, λc = 2 and λr = 4 are used for tiered Imagenet, and λc = 1 and λr = 2 are used for CIFAR-FS. ... we set the initial learning rate to 0.00001 and then decay it by 0.1 at epochs 50, 80 and 90, respectively. ... with a weight decay of 0.001.