Skip to Main content Skip to Navigation
Journal articles

Adding geodesic information and stochastic patch-wise image prediction for small dataset learning

Abstract : Most recent methods of image augmentation and prediction are building upon the deep learning paradigm. A careful preparation of the image dataset and the choice of a suitable network architecture are crucial steps to assess the desired image features and, thence, achieve accurate predictions. We first propose to help the learning process by adding structural information with specific distance transform to the input image data. To handle cases with limited number of training samples, we propose a patch-based procedure with a stratified sampling method at inference. We validate our approaches on two image datasets, corresponding to two different tasks. The ability of our method to segment and predict images is investigated through the ISBI 2012 segmentation challenge dataset and generated electric field masks, respectively. The obtained results are evaluated using appropriate metrics: VRand for image segmentation and SSIM, UIQ and PSNR for image prediction. The proposed techniques demonstrate that the established framework is a reliable estimation method that could be used for a wide range of applications.
Complete list of metadata
Contributor : Nadine Couëdel Connect in order to contact the contributor
Submitted on : Monday, September 6, 2021 - 2:01:39 PM
Last modification on : Saturday, June 25, 2022 - 9:24:29 AM


Publisher files allowed on an open archive


Distributed under a Creative Commons Attribution - NonCommercial - NoDerivatives 4.0 International License



Adam Hammoumi, Maxime Moreaud, Christophe Ducottet, Sylvain Desroziers. Adding geodesic information and stochastic patch-wise image prediction for small dataset learning. Neurocomputing, Elsevier, 2021, 456, pp.481-491. ⟨10.1016/j.neucom.2021.01.108⟩. ⟨hal-02879709v3⟩



Record views


Files downloads