# Rethinking Unsupervised Neural Superpixel Segmentation

arXiv: https://arxiv.org/abs/2206.10213 · HTML: https://mlsanity.com/paper/2206.10213/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 21 Jun 2022.

## Builds on (most cited first, 9 of 9)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Superpixel Segmentation with Fully Convolutional Networks](https://mlsanity.com/paper/2003.12929/) (2020)
- [Superpixel Segmentation via Convolutional Neural Networks with Regularized Information Maximization](https://mlsanity.com/paper/2002.06765/) (2020)
- [AINet+: Advancing Superpixel Segmentation via Cascaded Association Implantation](https://mlsanity.com/paper/2101.10696/) (2021)

## Built on by (most cited first, 3 of 3)

- [Unsupervised Image Semantic Segmentation through Superpixels and Graph Neural Networks](https://mlsanity.com/paper/2210.11810/) (2022)
- [Unsupervised Superpixel Generation using Edge-Sparse Embedding](https://mlsanity.com/paper/2211.15474/) (2022)
- [Semi-Automated Segmentation of Geoscientific Data Using Superpixels](https://mlsanity.com/paper/2303.11404/) (2023)

## Abstract (arXiv)

Recently, the concept of unsupervised learning for superpixel segmentation via CNNs has been studied. Essentially, such methods generate superpixels by convolutional neural network (CNN) employed on a single image, and such CNNs are trained without any labels or further information. Thus, such approach relies on the incorporation of priors, typically by designing an objective function that guides the solution towards a meaningful superpixel segmentation. In this paper we propose three key elements to improve the efficacy of such networks: (i) the similarity of the soft superpixelated image compared to the input image, (ii) the enhancement and consideration of object edges and boundaries and (iii) a modified architecture based on atrous convolution, which allow for a wider field of view, functioning as a multi-scale component in our network. By experimenting with the BSDS500 dataset, we find evidence to the significance of our proposal, both qualitatively and quantitatively.