# Superpixel Segmentation via Convolutional Neural Networks with Regularized Information Maximization

arXiv: https://arxiv.org/abs/2002.06765 · HTML: https://mlsanity.com/paper/2002.06765/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2020.

## Built on by (most cited first, 10 of 10)

- [Learning the Superpixel in a Non-iterative and Lifelong Manner](https://mlsanity.com/paper/2103.10681/) (2021)
- [A comprehensive review and new taxonomy on superpixel segmentation](https://mlsanity.com/paper/2409.19179/) (2024)
- [Efficient Multiscale Object-based Superpixel Framework](https://mlsanity.com/paper/2204.03533/) (2022)
- [Rethinking Unsupervised Neural Superpixel Segmentation](https://mlsanity.com/paper/2206.10213/) (2022)
- [Implicit Integration of Superpixel Segmentation into Fully Convolutional Networks](https://mlsanity.com/paper/2103.03435/) (2021)
- [Deep Superpixel-based Network for Blind Image Quality Assessment](https://mlsanity.com/paper/2110.06564/) (2021)
- [HCFormer: Unified Image Segmentation with Hierarchical Clustering](https://mlsanity.com/paper/2205.09949/) (2022)
- [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)

We propose an unsupervised superpixel segmentation method by optimizing a randomly-initialized convolutional neural network (CNN) in inference time. Our method generates superpixels via CNN from a single image without any labels by minimizing a proposed objective function for superpixel segmentation in inference time. There are three advantages to our method compared with many of existing methods: (i) leverages an image prior of CNN for superpixel segmentation, (ii) adaptively changes the number of superpixels according to the given images, and (iii) controls the property of superpixels by adding an auxiliary cost to the objective function. We verify the advantages of our method quantitatively and qualitatively on BSDS500 and SBD datasets.