Instance Separation Emerges from Inpainting
arXiv:2003.00891
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.
References in corpus (6)
- EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
- MONet: Unsupervised Scene Decomposition and Representation
- Learning visual groups from co-occurrences in space and time
- Selfie: Self-supervised Pretraining for Image Embedding
- High Resolution Face Completion with Multiple Controllable Attributes via Fully End-to-End Progressive Generative Adversarial Networks
- SEIGAN: Towards Compositional Image Generation by Simultaneously Learning to Segment, Enhance, and Inpaint