PEELING proposes a novel approach for adversarial testing in the VG task by reducing properties in expressions. The method outperforms baselines in detecting issues and improves the accuracy of the VG model. By combining two perturbations, PEELING achieves superior results compared to individual perturbations.
The study evaluates PEELING on three datasets, RefCOCO, RefCOCO+, and RefCOCOg, showcasing its effectiveness in generating adversarial tests that enhance issue detection and improve model accuracy. The results demonstrate the importance of considering multimodal information in adversarial testing for VG models.
Key contributions include proposing a text perturbation approach based on image-aware property reduction, conducting comprehensive experiments to evaluate PEELING's effectiveness, and providing a public reproduction package.
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Zhiyuan Chan... at arxiv.org 03-05-2024
https://arxiv.org/pdf/2403.01118.pdfDeeper Inquiries