Mask-guided sample selection for semi-supervised instance segmentation
Visualitza/Obre
Cita com:
hdl:2117/328619
Tipus de documentArticle
Data publicació2020-07-05
Condicions d'accésAccés obert
Tots els drets reservats. Aquesta obra està protegida pels drets de propietat intel·lectual i
industrial corresponents. Sense perjudici de les exempcions legals existents, queda prohibida la seva
reproducció, distribució, comunicació pública o transformació sense l'autorització del titular dels drets
Abstract
Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. Weakly-supervised pipelines are the most common solution to address this constraint because they are trained with lower forms of supervision, such as bounding boxes or scribbles. Semi-supervised methods are another option, that leverage a large amount of unlabeled data and a limited number of strongly-labeled samples. In this second setup, samples to be strongly-annotated can be selected randomly or with an active learning mechanism that chooses the ones that will maximize the model performance. In this work, we propose a sample selection approach to decide which samples to annotate for semi-supervised instance segmentation. Our method consists in first predicting pseudo-masks for the unlabeled pool of samples, together with a score predicting the quality of each mask. This score is an estimate of the Intersection Over Union (IoU) of the segment with the ground truth mask. We study which samples should be annotated based on the quality score, leading to an improved performance for semi-supervised instance segmentation with low annotation budgets.
Descripció
The final publication is available at Springer via http://dx.doi.org/10.1007/s11042-020-09235-4
CitacióBellver, M. [et al.]. Mask-guided sample selection for semi-supervised instance segmentation. "Multimedia tools and applications", 5 Juliol 2020, vol. 79, p. 25551-25569.
ISSN1380-7501
Versió de l'editorhttps://link.springer.com/article/10.1007/s11042-020-09235-4
Col·leccions
- Computer Sciences - Articles de revista [318]
- Departament d'Arquitectura de Computadors - Articles de revista [1.049]
- Departament de Teoria del Senyal i Comunicacions - Articles de revista [2.526]
- CAP - Grup de Computació d'Altes Prestacions - Articles de revista [382]
- Doctorat en Teoria del Senyal i Comunicacions - Articles de revista [211]
- Doctorat en Arquitectura de Computadors - Articles de revista [164]
- GPI - Grup de Processament d'Imatge i Vídeo - Articles de revista [118]
Fitxers | Descripció | Mida | Format | Visualitza |
---|---|---|---|---|
aBellver.pdf | Accepted version | 2,203Mb | Visualitza/Obre |