mlsanityData to 7 Oct 2026

MaskSplit: Self-supervised Meta-learning for Few-shot Semantic Segmentation

arXiv 2110.12207 ↗First posted 23 Oct 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Just like other few-shot learning problems, few-shot segmentation aims to minimize the need for manual annotation, which is particularly costly in segmentation tasks. Even though the few-shot setting reduces this cost for novel test classes, there is still a need to annotate the training data. To alleviate this need, we propose a self-supervised training approach for learning few-shot segmentation models. We first use unsupervised saliency estimation to obtain pseudo-masks on images. We then train a simple prototype based model over different splits of pseudo masks and augmentations of images. Our extensive experiments show that the proposed approach achieves promising results, highlighting the potential of self-supervised training. To the best of our knowledge this is the first work that addresses unsupervised few-shot segmentation problem on natural images.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 44 of its 66 references that are in the map. First posted on arXiv 23 Oct 2021.

Builds on

44 of 66 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  7. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  8. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  9. 2016Pyramid Scene Parsing Networkcited by 2,472
  10. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  11. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  12. 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
32 more
  1. 2016Context Encoders: Feature Learning by Inpaintingcited by 1,424
  2. 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
  3. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  4. 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
  5. 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
  6. 2018Dual Attention Network for Scene Segmentationcited by 1,001
  7. 2018CCNet: Criss-Cross Attention for Semantic Segmentationcited by 717
  8. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
  9. 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 454
  10. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  11. 2017One-Shot Learning for Semantic Segmentationcited by 337
  12. 2018Context Encoding for Semantic Segmentationcited by 289
  13. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  14. 2017Unsupervised Representation Learning by Sorting Sequencescited by 219
  15. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  16. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  17. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  18. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  19. 2021Unsupervised Semantic Segmentation by Contrasting Object Mask Proposalscited by 190
  20. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  21. 2015ParseNet: Looking Wider to See Bettercited by 176
  22. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  23. 2014Simultaneous Detection and Segmentationcited by 158
  24. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  25. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  26. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  27. 2018Unsupervised Learning via Meta-Learningcited by 81
  28. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  29. 2020Autoregressive Unsupervised Image Segmentationcited by 60
  30. 2019DeepUSPS: Deep Robust Unsupervised Saliency Prediction With Self-Supervisioncited by 38
  31. 2020Self-Supervised Tuning for Few-Shot Segmentationcited by 17
  32. 2019Adaptive Masked Proxies for Few-Shot Segmentationcited by 8

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 2.

6 papers.

  1. 2022Visual Semantic Segmentation Based on Few/Zero-Shot Learning: An Overviewcited by 16
  2. 2023Meta-Optimization for Higher Model Generalizability in Single-Image Depth Predictioncited by 3
  3. 2023Unleash Model Potential: Bootstrapped Meta Self-supervised Learningcited by 2
  4. 2024Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Imagescited by 1
  5. 2025Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bankcited by 0
  6. 2025Dual-Branch Center-Surrounding Contrast: Rethinking Contrastive Learning for 3D Point Cloudscited by 0