mlsanityData to 14 Oct 2026

Meta-Learning for Multi-Label Few-Shot Classification

arXiv 2110.13494 ↗First posted 26 Oct 2021cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Even with the luxury of having abundant data, multi-label classification is widely known to be a challenging task to address. This work targets the problem of multi-label meta-learning, where a model learns to predict multiple labels within a query (e.g., an image) by just observing a few supporting examples. In doing so, we first propose a benchmark for Few-Shot Learning (FSL) with multiple labels per sample. Next, we discuss and extend several solutions specifically designed to address the conventional and single-label FSL, to work in the multi-label regime. Lastly, we introduce a neural module to estimate the label count of a given sample by exploiting the relational inference. We will show empirically the benefit of the label count module, the label propagation algorithm, and the extensions of conventional FSL methods on three challenging datasets, namely MS-COCO, iMaterialist, and Open MIC. Overall, our thorough experiments suggest that the proposed label-propagation algorithm in conjunction with the neural label count module (NLC) shall be considered as the method of choice.

Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). Builds on 31 of its 58 references that are in the map. First posted on arXiv 26 Oct 2021.

Builds on

31 of 58 references.

References · 31

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  4. 2016Matching Networks for One Shot Learningcited by 2,255
  5. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  6. 2019CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learningcited by 217
  7. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 211
  8. 2016CNN-RNN: A Unified Framework for Multi-label Image Classificationcited by 190
  9. 2017Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classificationcited by 85
  10. 2017Multi-label Image Recognition by Recurrently Discovering Attentional Regionscited by 83
  11. 2019Few-Shot Learning via Saliency-guided Hallucination of Samplescited by 49
  12. 2017Improving Pairwise Ranking for Multi-label Image Classificationcited by 40
19 more
  1. 2015Exploit Bounding Box Annotations for Multi-label Object Recognitioncited by 39
  2. 2019LaSO: Label-Set Operations networks for multi-label few-shot learningcited by 38
  3. 2019The iMaterialist Fashion Attribute Datasetcited by 37
  4. 2019Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classificationcited by 36
  5. 2021Few-shot Language Coordination by Modeling Theory of Mindcited by 32
  6. 2020Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learningcited by 31
  7. 2020Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classificationcited by 27
  8. 2016Domain Adaptation by Mixture of Alignments of Second- or Higher-Order Scatter Tensorscited by 18
  9. 2021Reinforced Attention for Few-Shot Learning and Beyondcited by 18
  10. 2016Learning an Invariant Hilbert Space for Domain Adaptationcited by 17
  11. 2018CNN-based Action Recognition and Supervised Domain Adaptation on 3D Body Skeletons via Kernel Feature Mapscited by 13
  12. 2018Power Normalizing Second-order Similarity Network for Few-shot Learningcited by 13
  13. 2020TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samplescited by 13
  14. 2018Zero-Shot Kernel Learningcited by 11
  15. 2019Identity-preserving Face Recovery from Stylized Portraitscited by 9
  16. 2021REFINE: Random RangE FInder for Network Embeddingcited by 9
  17. 2019Recovering Faces from Portraits with Auxiliary Facial Attributescited by 6
  18. 2018Model Selection for Generalized Zero-shot Learningcited by 4
  19. 2018Artwork Identification from Wearable Camera Images for Enhancing Experience of Museum Audiencescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 1; 2023: 9; 2024: 3; 2025: 4; 2026: 3.

21 papers.

Sort:

By area:

  1. 2022Texts as Images in Prompt Tuning for Multi-Label Image Recognitioncited by 51
  2. 2023Transductive Few-shot Learning with Prototype-based Label Propagation by Iterative Graph Refinementcited by 30
  3. 2021Few-shot Keypoint Detection with Uncertainty Learning for Unseen Speciescited by 27
  4. 2023Learning to Learn from APIs: Black-Box Data-Free Meta-Learningcited by 18
  5. 2024TAI++: Text as Image for Multi-Label Image Classification by Co-Learning Transferable Promptcited by 14
  6. 2023Architecture, Dataset and Model-Scale Agnostic Data-free Meta-Learningcited by 10
  7. 2024Data-free Multi-label Image Recognition via LLM-powered Prompt Tuningcited by 8
  8. 2024LC-Protonets: Multi-Label Few-Shot Learning for World Music Audio Taggingcited by 7
  9. 2023Task-Distributionally Robust Data-Free Meta-Learningcited by 4
  10. 2023Knowledge-Enhanced Multi-Label Few-Shot Product Attribute-Value Extractioncited by 3
  11. 2023Text as Image: Learning Transferable Adapter for Multi-Label Classificationcited by 3
  12. 2025Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuningcited by 3
9 more
  1. 2023Exploiting Field Dependencies for Learning on Categorical Datacited by 2
  2. 2025Dual-View Alignment Learning with Hierarchical-Prompt for Class-Imbalance Multi-Label Classificationcited by 2
  3. 2023Generalized Cross-domain Multi-label Few-shot Learning for Chest X-rayscited by 1
  4. 2023Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object Structure via HyperNetworkscited by 1
  5. 2025Text to Image for Multi-Label Image Recognition with Joint Prompt-Adapter Learningcited by 1
  6. 2025Efficient Masked Attention Transformer for Few-Shot Classification and Segmentationcited by 0
  7. 2026RAPT: Retrieval-Augmented Post-hoc Thresholding for Multi-Label Classificationcited by 0
  8. 2026Adapting Dense Vision-Language Relationships for Multi-label Classification with Partial Labelcited by 0
  9. 2026Purification and Regulation: Comorbidity-Aware Multi-Label Few-Shot Learning for Medical Image Classificationcited by 0