# Superpixel Integrated Grids for Fast Image Segmentation

arXiv: https://arxiv.org/abs/2510.06487 · HTML: https://mlsanity.com/paper/2510.06487/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [Superpixel Sampling Networks](https://mlsanity.com/paper/1807.10174/) (2018)
- [Superpixel Segmentation with Fully Convolutional Networks](https://mlsanity.com/paper/2003.12929/) (2020)
- [Superpixel Convolutional Networks using Bilateral Inceptions](https://mlsanity.com/paper/1511.06739/) (2015)
- [Superpixel Image Classification with Graph Attention Networks](https://mlsanity.com/paper/2002.05544/) (2020)
- [Superpixel Transformers for Efficient Semantic Segmentation](https://mlsanity.com/paper/2309.16889/) (2023)
- [HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation](https://mlsanity.com/paper/2106.03755/) (2021)
- [Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial Imagery](https://mlsanity.com/paper/2104.10249/) (2021)

## Abstract (arXiv)

Superpixels have long been used in image simplification to enable more efficient data processing and storage. However, despite their computational potential, their irregular spatial distribution has often forced deep learning approaches to rely on specialized training algorithms and architectures, undermining the original motivation for superpixelations. In this work, we introduce a new superpixel-based data structure, SIGRID (Superpixel-Integrated Grid), as an alternative to full-resolution images in segmentation tasks. By leveraging classical shape descriptors, SIGRID encodes both color and shape information of superpixels while substantially reducing input dimensionality. We evaluate SIGRIDs on four benchmark datasets using two popular convolutional segmentation architectures. Our results show that, despite compressing the original data, SIGRIDs not only match but in some cases surpass the performance of pixel-level representations, all while significantly accelerating model training. This demonstrates that SIGRIDs achieve a favorable balance between accuracy and computational efficiency.