mlsanityData to 7 Oct 2026

Boosting Few-shot Semantic Segmentation with Transformers

arXiv 2108.02266 ↗First posted 4 Aug 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentation has attracted lots of research attention. Previous arts extract features from support and query images, which are processed jointly before making predictions on query images. The whole process is based on convolutional neural networks (CNN), leading to the problem that only local information is used. In this paper, we propose a TRansformer-based Few-shot Semantic segmentation method (TRFS). Specifically, our model consists of two modules: Global Enhancement Module (GEM) and Local Enhancement Module (LEM). GEM adopts transformer blocks to exploit global information, while LEM utilizes conventional convolutions to exploit local information, across query and support features. Both GEM and LEM are complementary, helping to learn better feature representations for segmenting query images. Extensive experiments on PASCAL-5i and COCO datasets show that our approach achieves new state-of-the-art performance, demonstrating its effectiveness.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 44 of its 54 references that are in the map. First posted on arXiv 4 Aug 2021.

Builds on

44 of 54 references.

References · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  7. 2020End-to-End Object Detection with Transformerscited by 7,384
  8. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  9. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  10. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  11. 2017Non-local Neural Networkscited by 2,290
  12. 2016Matching Networks for One Shot Learningcited by 2,246
32 more
  1. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  2. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  3. 2019Transformer-XL: Attentive Language Models Beyond a Fixed-Length Contextcited by 1,830
  4. 2020Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformerscited by 1,368
  5. 2021Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetcited by 1,096
  6. 2021Transformers in Vision: A Surveycited by 1,009
  7. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  8. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  9. 2020End-to-End Video Instance Segmentation with Transformerscited by 443
  10. 2017One-Shot Learning for Semantic Segmentationcited by 337
  11. 2016ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentationcited by 330
  12. 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
  13. 2015What's the Point: Semantic Segmentation with Point Supervisioncited by 297
  14. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  15. 2015BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentationcited by 238
  16. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  17. 2015Conditional Random Fields as Recurrent Neural Networkscited by 213
  18. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  19. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
  20. 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
  21. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  22. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  23. 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
  24. 2014Simultaneous Detection and Segmentationcited by 158
  25. 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
  26. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  27. 2021TransCrowd: weakly-supervised crowd counting with transformerscited by 61
  28. 2015Semantic Image Segmentation via Deep Parsing Networkcited by 44
  29. 2021Transformer-Based Source-Free Domain Adaptationcited by 30
  30. 2021Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Imagescited by 27
  31. 2021Cloth Interactive Transformer for Virtual Try-Oncited by 15
  32. 2019Adaptive Masked Proxies for Few-Shot Segmentationcited by 8

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 2.

6 papers.

  1. 2022Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentationcited by 114
  2. 2022Dense Cross-Query-and-Support Attention Weighted Mask Aggregation for Few-Shot Segmentationcited by 65
  3. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  4. 2021Cost Aggregation Is All You Need for Few-Shot Segmentationcited by 16
  5. 2023Iterative Few-shot Semantic Segmentation from Image Label Textcited by 10
  6. 2023Multi-task Explainable Skin Lesion Classificationcited by 1