Instance separation emerges from inpainting
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-supervis...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article (Journal) Chapter/Article |
| Language: | English |
| Published: |
28 Feb 2020
|
| In: |
Arxiv
Year: 2020, Pages: 1-11 |
| DOI: | 10.48550/arXiv.2003.00891 |
| Online Access: | Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.2003.00891 Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/2003.00891 
|
| Author Notes: | Steffen Wolf, Fred A. Hamprecht, Jan Funke |
| Summary: | 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. |
|---|---|
| Item Description: | Gesehen am 13.07.2022 |
| Physical Description: | Online Resource |
| DOI: | 10.48550/arXiv.2003.00891 |