RUBi: Reducing Unimodal Biases for Visual Question Answering

Authors: Remi Cadene, Corentin Dancette, Hedi Ben younes, Matthieu Cord, Devi Parikh

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We run extensive experiments on VQA-CP v2 [10] and demonstrate the ability of RUBi to surpass current state-of-the-art results from a significant margin.
Researcher Affiliation Collaboration 1 Sorbonne Université, CNRS, LIP6, 4 place Jussieu, 75005 Paris, 2 Facebook AI Research, 3 Georgia Institute of Technology
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes Our code is available: github.com/cdancette/rubi.bootstrap.pytorch
Open Datasets Yes We train and evaluate our models on VQA-CP v2 [10]. ... We also evaluate our models on the standard VQA v2 dataset [9].
Dataset Splits Yes We train and evaluate our models on VQA-CP v2 [10]. This dataset was developed to evaluate the models robustness to question biases. We follow the same training and evaluation protocol as [25], who also propose a learning strategy to reduce biases. For each model, we report the standard VQA evaluation metric [8]. We also evaluate our models on the standard VQA v2 [9]." and "VQA v2 train, val and test sets follow the same distribution
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions software components like 'Faster R-CNN' and 'GRU' but does not provide specific version numbers for these or other software dependencies.
Experiment Setup No The paper states 'Further implementation details are included in the supplementary materials,' indicating that specific experimental setup details, such as hyperparameters, are not provided in the main text.