Instance separation emerges from inpainting

• Verfasst von: Wolf, Steffen [VerfasserIn]
• Verfasst von: Hamprecht, Fred [VerfasserIn]
• Verfasst von: Funke, Jan [VerfasserIn]
• Titel: Instance separation emerges from inpainting
• Verf.angabe: Steffen Wolf, Fred A. Hamprecht, Jan Funke
• E-Jahr: 2020
• Jahr: 28 Feb 2020
• Umfang: 11 S.
• Fussnoten: Gesehen am 13.07.2022
• Titel Quelle: Enthalten in: De.arxiv.org
• Ort Quelle: [S.l.] : Arxiv.org, 1991
• Jahr Quelle: 2020
• Band/Heft Quelle: (2020), Artikel-ID 2003.0089, Seite 1-11
• DOI: doi:10.48550/arXiv.2003.00891
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Computer Science - Computer Vision and Pattern Recognition
• Sach-SW: Computer Science - Machine Learning
• Sach-SW: Statistics - Machine Learning
• K10plus-PPN: 1810085063

Abstract

Deep neural networks trained to inpaint partially occluded images show a deep understanding of image composition and have even been shown to remove objects from images convincingly. In this work, we investigate how this implicit knowledge of image composition can be leveraged for fully self-supervised instance separation. We propose a measure for the independence of two image regions given a fully self-supervised inpainting network and separate objects by maximizing this independence. We evaluate our method on two microscopy image datasets and show that it reaches similar segmentation performance to fully supervised methods.