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 and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

Revisit Multimodal Meta-Learning through the Lens of Multi-Task Learning

Authors: Milad Abdollahzadeh, Touba Malekzadeh, Ngai-Man (Man) Cheung

NeurIPS 2021 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the proposed model in both multimodal and unimodal few-shot classification scenarios.
Researcher Affiliation Academia Milad Abdollahzadeh, Touba Malekzadeh, Ngai-Man Cheung Singapore University of Technology and Design EMAIL
Pseudocode Yes Algorithm 1: Measuring Transference on a Target Task.
Open Source Code Yes The code for this project is available at https://miladabd.github.io/KML.
Open Datasets Yes We combine multiple widely used datasets (Omniglot [47], mini-Imagenet [12], FC100 [48], CUB [49], and Aircraft [50]).
Dataset Splits No The paper mentions 'meta-training' and 'meta-test' sets and 'support set' and 'query set' within tasks, but does not provide specific percentages or counts for overall training, validation, and test data splits of the datasets used.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or memory specifications used for running experiments.
Software Dependencies No The paper mentions using specific meta-learners and modifying existing code but does not provide version numbers for any software dependencies.
Experiment Setup No The details of the experimental setup can be found in the supplementary.