Recurrent instance segmentation

Conference item

Instance segmentation is the problem of detecting and delineating each distinct object of interest appearing in an image. Current instance segmentation approaches consist of ensembles of modules that are trained independently of each other, thus missing opportunities for joint learning. Here we propose a new instance segmentation paradigm consisting in an end-to-end method that learns how to segment instances sequentially. The model is based on a recurrent neural network that sequentially finds objects and their segmentations one at a time. This net is provided with a spatial memory that keeps track of what pixels have been explained and allows occlusion handling. In order to train the model we designed a principled loss function that accurately represents the properties of the instance segmentation problem. In the experiments carried out, we found that our method outperforms recent approaches on multiple person segmentation, and all state of the art approaches on the Plant Phenotyping dataset for leaf counting.

Authors: Romera-Paredes, B; Torr, P

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Springer Verlag
• Host title: European Conference on Computer Vision 2016: Computer Vision – ECCV 2016
• Journal: ECCV 2016: Computer Vision – ECCV 2016
• Volume: 9910
• Pages: 312-329
• Series: Lecture Notes in Computer Science
• Publication date: 2016-09-17
• Acceptance date: 2016-07-11
• DOI: 10.1007/978-3-319-46466-4_19
• EISSN: 1611-3349
• ISSN: 0302-9743
• ISBN: 9783319464657