Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1]

Task-Specific Preconditioner for Cross-Domain Few-Shot Learning

Authors: Suhyun Kang, Jungwon Park, Wonseok Lee, Wonjong Rhee

AAAI 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical evaluations on the Meta-Dataset show that TSP achieves state-of-the-art performance across diverse experimental scenarios.
Researcher Affiliation Collaboration 1 Samsung Research, Seoul, South Korea 2 Department of Intelligence and Information, Seoul National University, Seoul, South Korea 3 IPAI, Seoul National University, Seoul, South Korea
Pseudocode Yes The algorithm for the training and testing procedures is provided in Appendix B.
Open Source Code No The paper states that baseline methods like TSA and TA2-Net are publicly available as open-source, but it does not provide an explicit statement or link for the code of the proposed method (TSP).
Open Datasets Yes In the experiments, we use Meta-Dataset (Triantafillou et al. 2019) that is the standard benchmark for evaluating the performance of CDFSL.
Dataset Splits Yes In all experiments, we follow the standard protocol described in (Triantafillou et al. 2019).
Hardware Specification No The paper mentions using ResNet-18 as the backbone for the feature extractor but does not provide specific details about the hardware (e.g., GPU models, CPU types) used for running the experiments.
Software Dependencies No The paper does not provide specific version numbers for any software components or libraries used (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup Yes For the Dataset Classifier Loss, weighting factor λ is set to 0.1, as it performs best compared to other values, as shown in Appendix D.1. Details of the Meta-Dataset, hyper-parameters, and additional implementation are available in Appendix E.