# Unsupervised Superpixel Generation using Edge-Sparse Embedding

arXiv: https://arxiv.org/abs/2211.15474 · HTML: https://mlsanity.com/paper/2211.15474/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 39 references that are in the map.
- First posted on arXiv 28 Nov 2022.

## Builds on (most cited first, 13 of 13)

- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks](https://mlsanity.com/paper/1810.03982/) (2018)
- ["Double-DIP": Unsupervised Image Decomposition via Coupled Deep-Image-Priors](https://mlsanity.com/paper/1812.00467/) (2018)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [SEEDS: Superpixels Extracted via Energy-Driven Sampling](https://mlsanity.com/paper/1309.3848/) (2013)
- [Denoising and Regularization via Exploiting the Structural Bias of Convolutional Generators](https://mlsanity.com/paper/1910.14634/) (2019)
- [Superpixel Convolutional Networks using Bilateral Inceptions](https://mlsanity.com/paper/1511.06739/) (2015)
- [Deep convolutional neural networks for segmenting 3D in vivo multiphoton images of vasculature in Alzheimer disease mouse models](https://mlsanity.com/paper/1801.00880/) (2018)
- [Learning the Superpixel in a Non-iterative and Lifelong Manner](https://mlsanity.com/paper/2103.10681/) (2021)
- [Superpixel Segmentation via Convolutional Neural Networks with Regularized Information Maximization](https://mlsanity.com/paper/2002.06765/) (2020)
- [Power-SLIC: Fast Superpixel Segmentations by Diagrams](https://mlsanity.com/paper/2012.11772/) (2020)
- [Rethinking Unsupervised Neural Superpixel Segmentation](https://mlsanity.com/paper/2206.10213/) (2022)

## Abstract (arXiv)

Partitioning an image into superpixels based on the similarity of pixels with respect to features such as colour or spatial location can significantly reduce data complexity and improve subsequent image processing tasks. Initial algorithms for unsupervised superpixel generation solely relied on local cues without prioritizing significant edges over arbitrary ones. On the other hand, more recent methods based on unsupervised deep learning either fail to properly address the trade-off between superpixel edge adherence and compactness or lack control over the generated number of superpixels. By using random images with strong spatial correlation as input, ie, blurred noise images, in a non-convolutional image decoder we can reduce the expected number of contrasts and enforce smooth, connected edges in the reconstructed image. We generate edge-sparse pixel embeddings by encoding additional spatial information into the piece-wise smooth activation maps from the decoder's last hidden layer and use a standard clustering algorithm to extract high quality superpixels. Our proposed method reaches state-of-the-art performance on the BSDS500, PASCAL-Context and a microscopy dataset.