mlsanityData to 14 Oct 2026

SEGA: Semantic Guided Attention on Visual Prototype for Few-Shot Learning

arXiv 2111.04316 ↗First posted 8 Nov 2021cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Teaching machines to recognize a new category based on few training samples especially only one remains challenging owing to the incomprehensive understanding of the novel category caused by the lack of data. However, human can learn new classes quickly even given few samples since human can tell what discriminative features should be focused on about each category based on both the visual and semantic prior knowledge. To better utilize those prior knowledge, we propose the SEmantic Guided Attention (SEGA) mechanism where the semantic knowledge is used to guide the visual perception in a top-down manner about what visual features should be paid attention to when distinguishing a category from the others. As a result, the embedding of the novel class even with few samples can be more discriminative. Concretely, a feature extractor is trained to embed few images of each novel class into a visual prototype with the help of transferring visual prior knowledge from base classes. Then we learn a network that maps semantic knowledge to category-specific attention vectors which will be used to perform feature selection to enhance the visual prototypes. Extensive experiments on miniImageNet, tieredImageNet, CIFAR-FS, and CUB indicate that our semantic guided attention realizes anticipated function and outperforms state-of-the-art results.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 41 of its 65 references that are in the map. First posted on arXiv 8 Nov 2021.

Builds on

41 of 65 references.

References · 41

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  6. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  7. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  8. 2014Going Deeper with Convolutionscited by 4,241
  9. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  10. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  11. 2016Matching Networks for One Shot Learningcited by 2,255
  12. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
29 more
  1. 2017Poincar'e Embeddings for Learning Hierarchical Representationscited by 684
  2. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  3. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
  4. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  5. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  6. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 437
  7. 2018Meta-learning with differentiable closed-form solverscited by 397
  8. 2018Dynamic Few-Shot Visual Learning without Forgettingcited by 385
  9. 2017Few-Shot Learning with Graph Neural Networkscited by 324
  10. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  11. 2018DropBlock: A regularization method for convolutional networkscited by 262
  12. 2019Cross Attention Network for Few-shot Classificationcited by 219
  13. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  14. 2020Negative Margin Matters: Understanding Margin in Few-shot Classificationcited by 129
  15. 2017Few-Shot Image Recognition by Predicting Parameters from Activationscited by 122
  16. 2019Adaptive Cross-Modal Few-Shot Learningcited by 95
  17. 2020Boosting Few-Shot Learning With Adaptive Margin Losscited by 83
  18. 2019Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learningcited by 69
  19. 2018Multi-level Semantic Feature Augmentation for One-shot Learningcited by 62
  20. 2019Small Data Challenges in Big Data Era: A Survey of Recent Progress on Unsupervised and Semi-Supervised Methodscited by 62
  21. 2019Associative Alignment for Few-shot Image Classificationcited by 58
  22. 2019Few-Shot Learning with Embedded Class Models and Shot-Free Meta Trainingcited by 57
  23. 2020Prototype Completion with Primitive Knowledge for Few-Shot Learningcited by 50
  24. 2018Low-shot Learning via Covariance-Preserving Adversarial Augmentation Networkscited by 35
  25. 2019TAFE-Net: Task-Aware Feature Embeddings for Low Shot Learningcited by 32
  26. 2019Baby steps towards few-shot learning with multiple semanticscited by 29
  27. 2019Knowledge Graph Transfer Network for Few-Shot Recognitioncited by 20
  28. 2018Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learningcited by 15
  29. 2020Cooperative Bi-path Metric for Few-shot Learningcited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 7; 2024: 2; 2025: 1; 2026: 2.

15 papers.

Sort:

By area:

  1. 2023Generating images of rare concepts using pre-trained diffusion modelscited by 79
  2. 2023Norm-guided latent space exploration for text-to-image generationcited by 43
  3. 2024A Comprehensive Review of Few-shot Action Recognitioncited by 11
  4. 2025Connecting Giants: Synergistic Knowledge Transfer of Large Multimodal Models for Few-Shot Learningcited by 9
  5. 2023Semantic-visual Guided Transformer for Few-shot Class-incremental Learningcited by 6
  6. 2022Function-words Enhanced Attention Networks for Few-Shot Inverse Relation Classificationcited by 5
  7. 2022Few-Shot Meta Learning for Recognizing Facial Phenotypes of Genetic Disorderscited by 1
  8. 2022Disentangled Generation with Information Bottleneck for Few-Shot Learningcited by 1
  9. 2023Co-Occurrence Matters: Learning Action Relation for Temporal Action Localizationcited by 1
  10. 2023Compositional Prototypical Networks for Few-Shot Classificationcited by 1
  11. 2023LPN: Language-guided Prototypical Network for few-shot classificationcited by 1
  12. 2024Dual-View Data Hallucination with Semantic Relation Guidance for Few-Shot Image Recognitioncited by 1
3 more
  1. 2026Rethinking the Good Enough Embedding for Easy Few-Shot Learningcited by 1
  2. 2023Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learningcited by 0
  3. 2026PMCE: Probabilistic Multi-Granularity Semantics with Caption-Guided Enhancement for Few-Shot Learningcited by 0