mlsanityData to 7 Oct 2026

Superpixel Sampling Networks

arXiv 1807.10174 ↗First posted 26 Jul 2018cs.CVcited by 79

Not on the map. Why?

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.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jul 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 13; 2023: 13; 2024: 13; 2025: 12; 2026: 11.

79 papers.

Sort:

  1. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  2. 2021Hierarchical Graph Representations in Digital Pathologycited by 58
  3. 2022Vision Transformer with Super Token Samplingcited by 43
  4. 2023Image as Set of Pointscited by 43
  5. 2022Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuningcited by 33
  6. 2023CLUSTSEG: Clustering for Universal Segmentationcited by 32
  7. 2023HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentationcited by 31
  8. 2022Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenescited by 23
  9. 2025CATANet: Efficient Content-Aware Token Aggregation for Lightweight Image Super-Resolutioncited by 15
  10. 2021Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularizationcited by 13
  11. 2024SPFormer: Enhancing Vision Transformer with Superpixel Representationcited by 13
  12. 2021Learning the Superpixel in a Non-iterative and Lifelong Mannercited by 12
38 more
  1. 2023DCN-T: Dual Context Network with Transformer for Hyperspectral Image Classificationcited by 12
  2. 2023SAAN: Similarity-aware attention flow network for change detection with VHR remote sensing imagescited by 12
  3. 2023Superpixel Transformers for Efficient Semantic Segmentationcited by 12
  4. 2022Point Label Aware Superpixels for Multi-species Segmentation of Underwater Imagerycited by 10
  5. 2024Dual-stage Hyperspectral Image Classification Model with Spectral Supertokencited by 9
  6. 20253D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformationcited by 9
  7. 2021HERS Superpixels: Deep Affinity Learning for Hierarchical Entropy Rate Segmentationcited by 8
  8. 2023Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervisioncited by 8
  9. 2024A comprehensive review and new taxonomy on superpixel segmentationcited by 8
  10. 2021Survey of Image Based Graph Neural Networkscited by 7
  11. 2021E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentationcited by 7
  12. 2021Spectral-Spatial Global Graph Reasoning for Hyperspectral Image Classificationcited by 6
  13. 2023ClusterFormer: Clustering As A Universal Visual Learnercited by 6
  14. 2024Superpixel Tokenization for Vision Transformers: Preserving Semantic Integrity in Visual Tokenscited by 6
  15. 2023Learning Geometry-aware Representations by Sketchingcited by 5
  16. 2024Learning Invariant Inter-pixel Correlations for Superpixel Generationcited by 5
  17. 2024Lagrangian Motion Fields for Long-term Motion Generationcited by 5
  18. 2025Gaussian Masked Autoencoderscited by 5
  19. 2022Efficient Multiscale Object-based Superpixel Frameworkcited by 4
  20. 2021DeepFH Segmentations for Superpixel-based Object Proposal Refinementcited by 3
  21. 2022Rethinking Unsupervised Neural Superpixel Segmentationcited by 3
  22. 2022SelectionConv: Convolutional Neural Networks for Non-rectilinear Image Datacited by 3
  23. 2025SuperCL: Superpixel Guided Contrastive Learning for Medical Image Segmentation Pre-trainingcited by 3
  24. 2025Superpixel Anything: A general object-based framework for accurate yet regular superpixel segmentationcited by 3
  25. 2021Implicit Integration of Superpixel Segmentation into Fully Convolutional Networkscited by 2
  26. 2021Adaptive Illumination based Depth Sensing using Deep Superpixel and Soft Sampling Approximationcited by 2
  27. 2021SIN:Superpixel Interpolation Networkcited by 2
  28. 2022Stereo Superpixel Segmentation Via Decoupled Dynamic Spatial-Embedding Fusion Networkcited by 2
  29. 2023Spatio-Temporal driven Attention Graph Neural Network with Block Adjacency matrix (STAG-NN-BA) for Remote Land-use Change Detectioncited by 2
  30. 2023Rethinking Superpixel Segmentation from Biologically Inspired Mechanismscited by 2
  31. 2024Superpixel Segmentation: A Long-Lasting Ill-Posed Problemcited by 2
  32. 2025Delving Deep into Semantic Relation Distillationcited by 2
  33. 2026STENet: Superpixel Token Enhancing Network for RGB-D Salient Object Detectioncited by 2
  34. 2021Heterogeneous Grid Convolution for Adaptive, Efficient, and Controllable Computationcited by 1
  35. 2021RSI-Net: Two-Stream Deep Neural Network for Remote Sensing Imagesbased Semantic Segmentationcited by 1
  36. 2021MSP : Refine Boundary Segmentation via Multiscale Superpixelcited by 1
  37. 2022Shape-Aware Masking for Inpainting in Medical Imagingcited by 1
  38. 2022Joint Sub-component Level Segmentation and Classification for Anomaly Detection within Dual-Energy X-Ray Security Imagerycited by 1

50 most cited of 79 All 79 (JSON)