mlsanityData to 14 Oct 2026

Few-shot Semantic Segmentation with Self-supervision from Pseudo-classes

arXiv 2110.11742 ↗First posted 22 Oct 2021cs.CV cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

Despite the success of deep learning methods for semantic segmentation, few-shot semantic segmentation remains a challenging task due to the limited training data and the generalisation requirement for unseen classes. While recent progress has been particularly encouraging, we discover that existing methods tend to have poor performance in terms of meanIoU when query images contain other semantic classes besides the target class. To address this issue, we propose a novel self-supervised task that generates random pseudo-classes in the background of the query images, providing extra training data that would otherwise be unavailable when predicting individual target classes. To that end, we adopted superpixel segmentation for generating the pseudo-classes. With this extra supervision, we improved the meanIoU performance of the state-of-the-art method by 2.5% and 5.1% on the one-shot tasks, as well as 6.7% and 4.4% on the five-shot tasks, on the PASCAL-5i and COCO benchmarks, respectively.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 20 of its 34 references that are in the map. First posted on arXiv 22 Oct 2021.

Builds on

20 of 34 references.

References · 20

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  2. 2017Mask R-CNNcited by 7,277
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  5. 2015Holistically-Nested Edge Detectioncited by 592
  6. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  7. 2017One-Shot Learning for Semantic Segmentationcited by 337
  8. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  9. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  10. 2021Adaptive Prototype Learning and Allocation for Few-Shot Segmentationcited by 207
  11. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  12. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
8 more
  1. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  2. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  3. 2014Simultaneous Detection and Segmentationcited by 159
  4. 2020Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?cited by 135
  5. 2020Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotationcited by 128
  6. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  7. 2019SegSort: Segmentation by Discriminative Sorting of Segmentscited by 96
  8. 2021Self-Guided and Cross-Guided Learning for Few-Shot Segmentationcited by 92

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 4.

6 papers.

  1. 2023RestNet: Boosting Cross-Domain Few-Shot Segmentation with Residual Transformation Networkcited by 17
  2. 2022Prototypical few-shot segmentation for cross-institution male pelvic structures with spatial registrationcited by 16
  3. 2023Iterative Few-shot Semantic Segmentation from Image Label Textcited by 10
  4. 2023Few Shot Semantic Segmentation: a review of methodologies, benchmarks, and open challengescited by 3
  5. 2023Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy Imagescited by 3
  6. 2022Online pseudo labeling for polyp segmentation with momentum networkscited by 1