0 avis
SuperpixelGridMasks Data Augmentation: Application to Precision Health and Other Real-world Data
Archive ouverte : Article de revue
Edité par HAL CCSD
ressources projet: https://github.com/hammoudiproject/SuperpixelGridMasksdatasets used for the article: 1 Dataset Chest X-Ray Images: https://www.kaggle.com/datasets/paultimothymooney/chest-xray-pneumonia2 A PASCAL VOC dataset: http://host.robots.ox.ac.uk/pascal/VOC/databases.html#VOC2005_1. International audience. A novel approach of data augmentation based on irregular superpixel decomposition is proposed. This approach called SuperpixelGridMasks permits to extend original image datasets that are required by training stages of machine learning-related analysis architectures towards increasing their performances. Three variants named SuperpixelGridCut, SuperpixelGridMean, and SuperpixelGridMix are presented. These grid-based methods produce a new style of image transformations using the dropping and fusing of information. Extensive experiments using various image classification models as well as precision health and surrounding real-world datasets show that baseline performances can be significantly outperformed using our methods. The comparative study also shows that our methods can overpass the performances of other data augmentations. SuperpixelGridCut, SuperpixelGridMean, and SuperpixelGridMix codes are publicly available at https://github.com/hammoudiproject/SuperpixelGridMasks.
Consulter en ligne
Suggestions
Du même auteur
Du même sujet
