Checkmate: interpretable and explainable RSVQA is the endgame
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918126634926080 |
|---|---|
| author | Tosato, Lucrezia Chappuis, Christel Tartini Montariol, Syrielle Weissgerber, Flora Lobry, Sylvain Tuia, Devis |
| author_facet | Tosato, Lucrezia Chappuis, Christel Tartini Montariol, Syrielle Weissgerber, Flora Lobry, Sylvain Tuia, Devis |
| contents | Remote Sensing Visual Question Answering (RSVQA) presents unique challenges in ensuring that model decisions are both understandable and grounded in visual content. Current models often suffer from a lack of interpretability and explainability, as well as from biases in dataset distributions that lead to shortcut learning. In this work, we tackle these issues by introducing a novel RSVQA dataset, Chessboard, designed to minimize biases through 3'123'253 questions and a balanced answer distribution. Each answer is linked to one or more cells within the image, enabling fine-grained visual reasoning.
Building on this dataset, we develop an explainable and interpretable model called Checkmate that identifies the image cells most relevant to its decisions. Through extensive experiments across multiple model architectures, we show that our approach improves transparency and supports more trustworthy decision-making in RSVQA systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_13086 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Checkmate: interpretable and explainable RSVQA is the endgame Tosato, Lucrezia Chappuis, Christel Tartini Montariol, Syrielle Weissgerber, Flora Lobry, Sylvain Tuia, Devis Computer Vision and Pattern Recognition Remote Sensing Visual Question Answering (RSVQA) presents unique challenges in ensuring that model decisions are both understandable and grounded in visual content. Current models often suffer from a lack of interpretability and explainability, as well as from biases in dataset distributions that lead to shortcut learning. In this work, we tackle these issues by introducing a novel RSVQA dataset, Chessboard, designed to minimize biases through 3'123'253 questions and a balanced answer distribution. Each answer is linked to one or more cells within the image, enabling fine-grained visual reasoning. Building on this dataset, we develop an explainable and interpretable model called Checkmate that identifies the image cells most relevant to its decisions. Through extensive experiments across multiple model architectures, we show that our approach improves transparency and supports more trustworthy decision-making in RSVQA systems. |
| title | Checkmate: interpretable and explainable RSVQA is the endgame |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.13086 |