Assessment of CNN-based methods for poverty estimation from satellite images Pattern Recognition : proceedings, part VII Jarry, R. Chaumont, M. /Berti-Equille, Laure Subsol, G One of the major issues in predicting poverty with satellite images is the lack of fine-grained and reliable poverty indicators. To address this problem, various methodologies were proposed recently. Most recent approaches use a proxy (e.g., nighttime light), as an additional information, to mitigate the problem of sparse data. They consist in building and training a CNN with a large set of images, which is then used as a feature extractor. Ultimately, pairs of extracted feature vectors and poverty labels are used to learn a regression model to predict the poverty indicators.First, we propose a rigorous comparative study of such approaches based on a unified framework and a common set of images. We observed that the geographic displacement on the spatial coordinates of poverty observations degrades the prediction performances of all the methods. Therefore, we present a new methodology combining grid-cell selection and ensembling that improves the poverty prediction to handle coordinate displacement. Springer Del Bimbo, A. (ed.) Cucchiara, R. (ed.) Sclaroff, S. (ed.) Farinella, G.M. (ed.) Mei, T. (ed.) Bertini, M. (ed.) Escalante, H.J. (ed.) Vezzani, R. (ed.) 2021 text https://www.documentation.ird.fr/hor/fdi:010085560 fdi:010085560 Jarry R., Chaumont M., Berti-Equille Laure, Subsol G, . Assessment of CNN-based methods for poverty estimation from satellite images. In : Del Bimbo A. (ed.), Cucchiara R. (ed.), Sclaroff S. (ed.), Farinella G.M. (ed.), Mei T. (ed.), Bertini M. (ed.), Escalante H.J. (ed.), Vezzani R. (ed.), . Pattern Recognition : proceedings, part VII Springer, ; 12667). 2021, 550-565 ICPR.International Workshops and Challenges, [En ligne], 2021/01/10-15 EN