Curriculum Learning for Compositional Visual Reasoning

Wafa Aissa, Wafa Aissa, Marin Ferecatu, Michel Crucianu

2023

Abstract

Visual Question Answering (VQA) is a complex task requiring large datasets and expensive training. Neural Module Networks (NMN) first translate the question to a reasoning path, then follow that path to analyze the image and provide an answer. We propose an NMN method that relies on predefined cross-modal embeddings to “warm start” learning on the GQA dataset, then focus on Curriculum Learning (CL) as a way to improve training and make a better use of the data. Several difficulty criteria are employed for defining CL methods. We show that by an appropriate selection of the CL method the cost of training and the amount of training data can be greatly reduced, with a limited impact on the final VQA accuracy. Furthermore, we introduce intermediate losses during training and find that this allows to simplify the CL strategy.

Paper Citation

in Harvard Style

Aissa W., Ferecatu M. and Crucianu M. (2023). Curriculum Learning for Compositional Visual Reasoning. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 888-897. DOI: 10.5220/0011895400003417

in Bibtex Style

@conference{visapp23,
author={Wafa Aissa and Marin Ferecatu and Michel Crucianu},
title={Curriculum Learning for Compositional Visual Reasoning},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={888-897},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011895400003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - Curriculum Learning for Compositional Visual Reasoning
SN - 978-989-758-634-7
AU - Aissa W.
AU - Ferecatu M.
AU - Crucianu M.
PY - 2023
SP - 888
EP - 897
DO - 10.5220/0011895400003417
PB - SciTePress