# Superpixel Sampling Networks

arXiv: https://arxiv.org/abs/1807.10174 · HTML: https://mlsanity.com/paper/1807.10174/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2018.

## Built on by (most cited first, 30 of 79)

- [Adaptive Prototype Learning and Allocation for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01893/) (2021)
- [Hierarchical Graph Representations in Digital Pathology](https://mlsanity.com/paper/2102.11057/) (2021)
- [Vision Transformer with Super Token Sampling](https://mlsanity.com/paper/2211.11167/) (2022)
- [Image as Set of Points](https://mlsanity.com/paper/2303.01494/) (2023)
- [Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning](https://mlsanity.com/paper/2210.01035/) (2022)
- [CLUSTSEG: Clustering for Universal Segmentation](https://mlsanity.com/paper/2305.02187/) (2023)
- [HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2305.13031/) (2023)
- [Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes](https://mlsanity.com/paper/2208.06671/) (2022)
- [CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2503.06896/) (2025)
- [Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization](https://mlsanity.com/paper/2107.00691/) (2021)
- [SPFormer: Enhancing Vision Transformer with Superpixel Representation](https://mlsanity.com/paper/2401.02931/) (2024)
- [Learning the Superpixel in a Non-iterative and Lifelong Manner](https://mlsanity.com/paper/2103.10681/) (2021)
- [DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classification](https://mlsanity.com/paper/2304.09915/) (2023)
- [SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing images](https://mlsanity.com/paper/2308.14570/) (2023)
- [Superpixel Transformers for Efficient Semantic Segmentation](https://mlsanity.com/paper/2309.16889/) (2023)
- [Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagery](https://mlsanity.com/paper/2202.13487/) (2022)
- [Dual-stage Hyperspectral Image Classification Model with Spectral Supertoken](https://mlsanity.com/paper/2407.07307/) (2024)
- [3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation](https://mlsanity.com/paper/2503.15185/) (2025)
- [HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentation](https://mlsanity.com/paper/2106.03755/) (2021)
- [Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision](https://mlsanity.com/paper/2303.05503/) (2023)
- [A comprehensive review and new taxonomy on superpixel segmentation](https://mlsanity.com/paper/2409.19179/) (2024)
- [Survey of Image Based Graph Neural Networks](https://mlsanity.com/paper/2106.06307/) (2021)
- [E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation](https://mlsanity.com/paper/2112.07106/) (2021)
- [Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokens](https://mlsanity.com/paper/2412.04680/) (2024)
- [Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classification](https://mlsanity.com/paper/2106.13952/) (2021)
- [ClusterFormer: Clustering As A Universal Visual Learner](https://mlsanity.com/paper/2309.13196/) (2023)
- [Learning Geometry-aware Representations by Sketching](https://mlsanity.com/paper/2304.08204/) (2023)
- [Learning Invariant Inter-pixel Correlations for Superpixel Generation](https://mlsanity.com/paper/2402.18201/) (2024)
- [Lagrangian Motion Fields for Long-term Motion Generation](https://mlsanity.com/paper/2409.01522/) (2024)
- [Gaussian Masked Autoencoders](https://mlsanity.com/paper/2501.03229/) (2025)

## Abstract (arXiv)

Superpixels provide an efficient low/mid-level representation of image data, which greatly reduces the number of image primitives for subsequent vision tasks. Existing superpixel algorithms are not differentiable, making them difficult to integrate into otherwise end-to-end trainable deep neural networks. We develop a new differentiable model for superpixel sampling that leverages deep networks for learning superpixel segmentation. The resulting "Superpixel Sampling Network" (SSN) is end-to-end trainable, which allows learning task-specific superpixels with flexible loss functions and has fast runtime. Extensive experimental analysis indicates that SSNs not only outperform existing superpixel algorithms on traditional segmentation benchmarks, but can also learn superpixels for other tasks. In addition, SSNs can be easily integrated into downstream deep networks resulting in performance improvements.