mlsanityData to 7 Oct 2026

Synthesized Classifiers for Zero-Shot Learning

arXiv 1603.00550 ↗First posted 2 Mar 2016cs.CVcited by 113

Not on the map. Why?

Abstract (arXiv)

Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which labeled examples are provided. We propose to tackle this problem from the perspective of manifold learning. Our main idea is to align the semantic space that is derived from external information to the model space that concerns itself with recognizing visual features. To this end, we introduce a set of "phantom" object classes whose coordinates live in both the semantic space and the model space. Serving as bases in a dictionary, they can be optimized from labeled data such that the synthesized real object classifiers achieve optimal discriminative performance. We demonstrate superior accuracy of our approach over the state of the art on four benchmark datasets for zero-shot learning, including the full ImageNet Fall 2011 dataset with more than 20,000 unseen classes.

Key facts. Cited by 113 papers in the map (data through 7 Oct 2026). First posted on arXiv 2 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 49; 2022: 31; 2023: 19; 2024: 8; 2025: 4; 2026: 1.

113 papers.

Sort:

By area:

  1. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  2. 2023Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entitiescited by 112
  3. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  4. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  5. 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
  6. 2022I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classificationcited by 54
  7. 2021Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentationcited by 53
  8. 2021OntoZSL: Ontology-enhanced Zero-shot Learningcited by 45
  9. 2021Zero-Shot Instance Segmentationcited by 40
  10. 2021Zero-Shot Learning on 3D Point Cloud Objects and Beyondcited by 38
  11. 2022DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learningcited by 33
  12. 2021TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learningcited by 28
38 more
  1. 2023A Systematic Review of Few-Shot Learning in Medical Imagingcited by 28
  2. 2022I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classificationcited by 27
  3. 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
  4. 2023Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Stylecited by 25
  5. 2021Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Surveycited by 23
  6. 2022Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attentioncited by 21
  7. 2022Open Long-Tailed Recognition in a Dynamic Worldcited by 21
  8. 2023See More and Know More: Zero-shot Point Cloud Segmentation via Multi-modal Visual Datacited by 21
  9. 2021Fine-Grained Zero-Shot Learning with DNA as Side Informationcited by 20
  10. 2022Hybrid Routing Transformer for Zero-Shot Learningcited by 20
  11. 2021Task Aligned Generative Meta-learning for Zero-shot Learningcited by 19
  12. 2021Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognitioncited by 19
  13. 2022Attribute Prototype Network for Any-Shot Learningcited by 19
  14. 2021Learning Robust Visual-semantic Mapping for Zero-shot Learningcited by 16
  15. 2021On Bridging Generic and Personalized Federated Learning for Image Classificationcited by 15
  16. 2023Image-free Classifier Injection for Zero-Shot Classificationcited by 15
  17. 2021Learning from Multiple Noisy Partial Labelerscited by 14
  18. 2021A New Split for Evaluating True Zero-Shot Action Recognitioncited by 14
  19. 2024AAPL: Adding Attributes to Prompt Learning for Vision-Language Modelscited by 14
  20. 2024Low-Resource Vision Challenges for Foundation Modelscited by 13
  21. 2021Disentangling Semantic-to-visual Confusion for Zero-shot Learningcited by 11
  22. 2021Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learningcited by 8
  23. 2021Attribute-Modulated Generative Meta Learning for Zero-Shot Classificationcited by 8
  24. 2022Submodlib: A Submodular Optimization Librarycited by 8
  25. 2023GBE-MLZSL: A Group Bi-Enhancement Framework for Multi-Label Zero-Shot Learningcited by 8
  26. 2021Prototype Completion for Few-Shot Learningcited by 7
  27. 2021Tell me what you see: A zero-shot action recognition method based on natural language descriptionscited by 7
  28. 2022A Survey on Visual Transfer Learning using Knowledge Graphscited by 7
  29. 2021CIZSL++: Creativity Inspired Generative Zero-Shot Learningcited by 6
  30. 2021Benchmarking Knowledge-driven Zero-shot Learningcited by 6
  31. 2021Region Semantically Aligned Network for Zero-Shot Learningcited by 6
  32. 2022How Robust are Discriminatively Trained Zero-Shot Learning Models?cited by 6
  33. 2022A Gating Model for Bias Calibration in Generalized Zero-shot Learningcited by 6
  34. 2023Federated Learning of Shareable Bases for Personalization-Friendly Image Classificationcited by 6
  35. 2023Attribute-Aware Representation Rectification for Generalized Zero-Shot Learningcited by 6
  36. 2021Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularizationcited by 5
  37. 2021Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen Domainscited by 5
  38. 2023Frustratingly Simple but Effective Zero-shot Detection and Segmentation: Analysis and a Strong Baselinecited by 5

50 most cited of 113 All 113 (JSON)