# Instance Separation Emerges from Inpainting

arXiv: https://arxiv.org/abs/2003.00891 · HTML: https://mlsanity.com/paper/2003.00891/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Feb 2020.

## Built on by (most cited first, 2 of 2)

- [Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy Images](https://mlsanity.com/paper/2310.08501/) (2023)
- [Towards Unsupervised Representation Learning: Learning, Evaluating and Transferring Visual Representations](https://mlsanity.com/paper/2312.00101/) (2023)

## Abstract (arXiv)

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.