mlsanityData to 14 Oct 2026

Dense Gaussian Processes for Few-Shot Segmentation

arXiv 2110.03674 ↗First posted 7 Oct 2021cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Few-shot segmentation is a challenging dense prediction task, which entails segmenting a novel query image given only a small annotated support set. The key problem is thus to design a method that aggregates detailed information from the support set, while being robust to large variations in appearance and context. To this end, we propose a few-shot segmentation method based on dense Gaussian process (GP) regression. Given the support set, our dense GP learns the mapping from local deep image features to mask values, capable of capturing complex appearance distributions. Furthermore, it provides a principled means of capturing uncertainty, which serves as another powerful cue for the final segmentation, obtained by a CNN decoder. Instead of a one-dimensional mask output, we further exploit the end-to-end learning capabilities of our approach to learn a high-dimensional output space for the GP. Our approach sets a new state-of-the-art on the PASCAL-5i and COCO-20i benchmarks, achieving an absolute gain of +8.4 mIoU in the COCO-20i 5-shot setting. Furthermore, the segmentation quality of our approach scales gracefully when increasing the support set size, while achieving robust cross-dataset transfer. Code and trained models are available at urlhttps://github.com/joakimjohnander/dgpnet.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 7 Oct 2021.

Builds on

32 of 47 references.

References · 32

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  8. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  9. 2015Deep Kernel Learningcited by 445
  10. 2017One-Shot Learning for Semantic Segmentationcited by 337
  11. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  12. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
20 more
  1. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  2. 2021Hypercorrelation Squeeze for Few-Shot Segmentationcited by 193
  3. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  4. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  5. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  6. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  7. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  8. 2021Few-Shot Segmentation via Cycle-Consistent Transformercited by 133
  9. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  10. 2018Learning a Discriminative Feature Network for Semantic Segmentationcited by 114
  11. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  12. 2019Infinite Mixture Prototypes for Few-Shot Learningcited by 99
  13. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92
  14. 2014Manifold Gaussian Processes for Regressioncited by 80
  15. 2021Mining Latent Classes for Few-shot Segmentationcited by 69
  16. 2021Learning Meta-class Memory for Few-Shot Semantic Segmentationcited by 56
  17. 2018Unveiling the Power of Deep Trackingcited by 41
  18. 2020On the Texture Bias for Few-Shot CNN Segmentationcited by 38
  19. 2020Bayesian Few-Shot Classification with One-vs-Each P'olya-Gamma Augmented Gaussian Processescited by 32
  20. 2019A New Local Transformation Module for Few-shot Segmentationcited by 15

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 8; 2024: 4; 2025: 3.

17 papers.

Sort:

By area:

  1. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
  2. 2024VRP-SAM: SAM with Visual Reference Promptcited by 75
  3. 2023SLiMe: Segment Like Mecited by 34
  4. 2023Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matchingcited by 29
  5. 2022Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentationcited by 23
  6. 2025DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistencycited by 15
  7. 2022CATrans: Context and Affinity Transformer for Few-Shot Segmentationcited by 7
  8. 2023Dense Affinity Matching for Few-Shot Segmentationcited by 5
  9. 2024Group-On: Boosting One-Shot Segmentation with Supportive Querycited by 3
  10. 2025ProSAM: Enhancing the Robustness of SAM-based Visual Reference Segmentation with Probabilistic Promptscited by 3
  11. 2023Holistic Prototype Attention Network for Few-Shot VOScited by 1
  12. 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstractcited by 0
5 more
  1. 2023Reflection Invariance Learning for Few-shot Semantic Segmentationcited by 0
  2. 2023SemiGPC: Distribution-Aware Label Refinement for Imbalanced Semi-Supervised Learning Using Gaussian Processescited by 0
  3. 2024Image to Pseudo-Episode: Boosting Few-Shot Segmentation by Unlabeled Datacited by 0
  4. 2024Gaussian Process Emulators for Few-Shot Segmentation in Cardiac MRIcited by 0
  5. 2025AdaSemSeg: An Adaptive Few-shot Semantic Segmentation of Seismic Faciescited by 0