mlsanityData to 7 Oct 2026

Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation

arXiv 2106.00184 ↗First posted 1 Jun 2021cs.CVcited by 23

Not on the map. Why?

Abstract (arXiv)

Encouraging progress in few-shot semantic segmentation has been made by leveraging features learned upon base classes with sufficient training data to represent novel classes with few-shot examples. However, this feature sharing mechanism inevitably causes semantic aliasing between novel classes when they have similar compositions of semantic concepts. In this paper, we reformulate few-shot segmentation as a semantic reconstruction problem, and convert base class features into a series of basis vectors which span a class-level semantic space for novel class reconstruction. By introducing contrastive loss, we maximize the orthogonality of basis vectors while minimizing semantic aliasing between classes. Within the reconstructed representation space, we further suppress interference from other classes by projecting query features to the support vector for precise semantic activation. Our proposed approach, referred to as anti-aliasing semantic reconstruction (ASR), provides a systematic yet interpretable solution for few-shot learning problems. Extensive experiments on PASCAL VOC and MS COCO datasets show that ASR achieves strong results compared with the prior works.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 1 Jun 2021.

Builds on

32 of 48 references.

References · 32

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2017Mask R-CNNcited by 7,259
  4. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2016Pyramid Scene Parsing Networkcited by 2,472
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  9. 2019A Closer Look at Few-shot Classificationcited by 679
  10. 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
  11. 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
  12. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
20 more
  1. 2017One-Shot Learning for Semantic Segmentationcited by 337
  2. 2020Prior Guided Feature Enrichment Network for Few-Shot Segmentationcited by 271
  3. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  4. 2020Prototype Mixture Models for Few-shot Semantic Segmentationcited by 190
  5. 2019Feature Weighting and Boosting for Few-Shot Segmentationcited by 189
  6. 2021Few-Shot Incremental Learning with Continually Evolved Classifierscited by 184
  7. 2018Low-Shot Learning from Imaginary Datacited by 181
  8. 2018SG-One: Similarity Guidance Network for One-Shot Semantic Segmentationcited by 169
  9. 2020Part-aware Prototype Network for Few-shot Semantic Segmentationcited by 162
  10. 2018Task-Agnostic Meta-Learning for Few-shot Learningcited by 151
  11. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  12. 2020Are Labels Always Necessary for Classifier Accuracy Evaluation?cited by 104
  13. 2020CRNet: Cross-Reference Networks for Few-Shot Segmentationcited by 101
  14. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  15. 2021Beyond Max-Margin: Class Margin Equilibrium for Few-shot Object Detectioncited by 80
  16. 2021Multiple instance active learning for object detectioncited by 77
  17. 2020DeepEMD: Differentiable Earth Mover's Distance for Few-Shot Learningcited by 49
  18. 2020SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentationcited by 27
  19. 2020Self-Supervised Tuning for Few-Shot Segmentationcited by 17
  20. 2020Selecting Relevant Features from a Multi-domain Representation for Few-shot Classificationcited by 11

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 14; 2023: 4; 2024: 2.

23 papers.

Sort:

  1. 2022Learning What Not to Segment: A New Perspective on Few-Shot Segmentationcited by 120
  2. 2022Self-Support Few-Shot Semantic Segmentationcited by 96
  3. 2022Intermediate Prototype Mining Transformer for Few-Shot Semantic Segmentationcited by 37
  4. 2022Integrative Few-Shot Learning for Classification and Segmentationcited by 25
  5. 2022Interclass Prototype Relation for Few-Shot Segmentationcited by 25
  6. 2022Mask Matching Transformer for Few-Shot Segmentationcited by 22
  7. 2023FECANet: Boosting Few-Shot Semantic Segmentation with Feature-Enhanced Context-Aware Networkcited by 22
  8. 2022MSANet: Multi-Similarity and Attention Guidance for Boosting Few-Shot Segmentationcited by 21
  9. 2023Learning Expressive Prompting With Residuals for Vision Transformerscited by 21
  10. 2021MFNet: Multi-class Few-shot Segmentation Network with Pixel-wise Metric Learningcited by 10
  11. 2023Iterative Few-shot Semantic Segmentation from Image Label Textcited by 10
  12. 2023Harmonizing Base and Novel Classes: A Class-Contrastive Approach for Generalized Few-Shot Segmentationcited by 8
11 more
  1. 2022CRCNet: Few-shot Segmentation with Cross-Reference and Region-Global Conditional Networkscited by 7
  2. 2021A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentationcited by 6
  3. 2024MSDNet: Multi-Scale Decoder for Few-Shot Semantic Segmentation via Transformer-Guided Prototypingcited by 5
  4. 2024Learnable Prompt for Few-Shot Semantic Segmentation in Remote Sensing Domaincited by 3
  5. 2021Zero-Shot Semantic Segmentation via Spatial and Multi-Scale Aware Visual Class Embeddingcited by 2
  6. 2022Proposal Distribution Calibration for Few-Shot Object Detectioncited by 2
  7. 2022Query Semantic Reconstruction for Background in Few-Shot Segmentationcited by 1
  8. 2022Contrastive Enhancement Using Latent Prototype for Few-Shot Segmentationcited by 0
  9. 2022CobNet: Cross Attention on Object and Background for Few-Shot Segmentationcited by 0
  10. 2022A Joint Framework Towards Class-aware and Class-agnostic Alignment for Few-shot Segmentationcited by 0
  11. 2022Progressively Dual Prior Guided Few-shot Semantic Segmentationcited by 0