Mask-guided sample selection for Semi-Supervised Instance Segmentation
| Autor: | Amaia Salvador, Xavier Giro-i-Nieto, Jordi Torres, Miriam Bellver |
|---|---|
| Přispěvatelé: | Universitat Politècnica de Catalunya. Doctorat en Arquitectura de Computadors, Universitat Politècnica de Catalunya. Doctorat en Teoria del Senyal i Comunicacions, Universitat Politècnica de Catalunya. Departament d'Arquitectura de Computadors, Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions, Barcelona Supercomputing Center, Universitat Politècnica de Catalunya. CAP - Grup de Computació d'Altes Prestacions, Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Active learning Computer Networks and Communications Computer science Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition 02 engineering and technology Semi-supervised learning Imatges -- Processament -- Tècniques digitals 0202 electrical engineering electronic engineering information engineering Media Technology Leverage (statistics) Segmentation Image processing -- Digital techniques Ground truth Image segmentation business.industry 020207 software engineering Pattern recognition So imatge i multimèdia::Creació multimèdia::Imatge digital [Àrees temàtiques de la UPC] Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo [Àrees temàtiques de la UPC] Hardware and Architecture Artificial intelligence business Software |
| Zdroj: | UPCommons. Portal del coneixement obert de la UPC Universitat Politècnica de Catalunya (UPC) |
| DOI: | 10.48550/arxiv.2008.11073 |
| Popis: | Image segmentation methods are usually trained with pixel-level annotations, which require significant human effort to collect. The most common solution to address this constraint is to implement weakly-supervised pipelines trained with lower forms of supervision, such as bounding boxes or scribbles. Another option are semi-supervised methods, which 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 the mask. This score is an estimate of the Intersection Over Union (IoU) of the segment with the ground truth mask. We study which samples are better to annotate given the quality score, and show how our approach outperforms a random selection, leading to improved performance for semi-supervised instance segmentation with low annotation budgets. Comment: Preprint submitted to Multimedia Tools and Applications |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|