Multi-task deep learning for image segmentation using recursive approximation tasks
| Autor: | Nicolas Papadakis, Rihuan Ke, Carola-Bibiane Schönlieb, Aurélie Bugeau, Mark Kirkland, Peter Schuetz |
|---|---|
| Přispěvatelé: | Department of Applied Mathematics and Theoretical Physics (DAMTP), University of Cambridge [UK] (CAM), Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS), Institut de Mathématiques de Bordeaux (IMB), Université Bordeaux Segalen - Bordeaux 2-Université Sciences et Technologies - Bordeaux 1 (UB)-Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS), European Project: 777826,NoMADS(2018), Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB), Université Bordeaux Segalen - Bordeaux 2-Université Sciences et Technologies - Bordeaux 1-Université de Bordeaux (UB)-Institut Polytechnique de Bordeaux (Bordeaux INP)-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Computer science Computer Vision and Pattern Recognition (cs.CV) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Task (project management) Machine Learning (cs.LG) [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing 0202 electrical engineering electronic engineering information engineering FOS: Electrical engineering electronic engineering information engineering Segmentation Sequence business.industry Deep learning Image and Video Processing (eess.IV) Pattern recognition Image segmentation Electrical Engineering and Systems Science - Image and Video Processing Object (computer science) Computer Graphics and Computer-Aided Design Constraint (information theory) Task analysis 020201 artificial intelligence & image processing Artificial intelligence business Software |
| Zdroj: | IEEE Transactions on Image Processing IEEE Transactions on Image Processing, 2021, 30, pp.3555-3567. ⟨10.1109/TIP.2021.3062726⟩ IEEE Transactions on Image Processing, Institute of Electrical and Electronics Engineers, 2021, 30, pp.3555-3567. ⟨10.1109/TIP.2021.3062726⟩ HAL |
| ISSN: | 1057-7149 |
| DOI: | 10.1109/TIP.2021.3062726⟩ |
| Popis: | International audience; Fully supervised deep neural networks for segmentation usually require a massive amount of pixel-level labels which are manually expensive to create. In this work, we develop a multi-task learning method to relax this constraint. We regard the segmentation problem as a sequence of approximation subproblems that are recursively defined and in increasing levels of approximation accuracy. The subproblems are handled by a framework that consists of 1) a segmentation task that learns from pixel-level ground truth segmentation masks of a small fraction of the images, 2) a recursive approximation task that conducts partial object regions learning and data-driven mask evolution starting from partial masks of each object instance, and 3) other problem oriented auxiliary tasks that are trained with sparse annotations and promote the learning of dedicated features. Most training images are only labeled by (rough) partial masks, which do not contain exact object boundaries, rather than by their full segmentation masks. During the training phase, the approximation task learns the statistics of these partial masks, and the partial regions are recursively increased towards object boundaries aided by the learned information from the segmentation task in a fully data-driven fashion. The network is trained on an extremely small amount of precisely segmented images and a large set of coarse labels. Annotations can thus be obtained in a cheap way. We demonstrate the efficiency of our approach in three applications with microscopy images and ultrasound images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|