mlsanityData to 7 Oct 2026

Label-Embedding for Image Classification

arXiv 1503.08677 ↗First posted 30 Mar 2015cs.CVcited by 164

Not on the map. Why?

Abstract (arXiv)

Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded in the space of attribute vectors. We introduce a function that measures the compatibility between an image and a label embedding. The parameters of this function are learned on a training set of labeled samples to ensure that, given an image, the correct classes rank higher than the incorrect ones. Results on the Animals With Attributes and Caltech-UCSD-Birds datasets show that the proposed framework outperforms the standard Direct Attribute Prediction baseline in a zero-shot learning scenario. Label embedding enjoys a built-in ability to leverage alternative sources of information instead of or in addition to attributes, such as e.g. class hierarchies or textual descriptions. Moreover, label embedding encompasses the whole range of learning settings from zero-shot learning to regular learning with a large number of labeled examples.

Key facts. Cited by 164 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Mar 2015.

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: 56; 2022: 44; 2023: 24; 2024: 22; 2025: 10; 2026: 7.

164 papers.

Sort:

By area:

  1. 2022Decomposing NeRF for Editing via Feature Field Distillationcited by 370
  2. 2022Expanding Language-Image Pretrained Models for General Video Recognitioncited by 320
  3. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  4. 2021Combined Scaling for Zero-shot Transfer Learningcited by 182
  5. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  6. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  7. 2022"This is my unicorn, Fluffy": Personalizing frozen vision-language representationscited by 95
  8. 2021Elaborative Rehearsal for Zero-shot Action Recognitioncited by 76
  9. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  10. 2021A Closer Look at Self-training for Zero-Label Semantic Segmentationcited by 57
  11. 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
  12. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
38 more
  1. 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
  2. 2023Enhancing CLIP with GPT-4: Harnessing Visual Descriptions as Promptscited by 48
  3. 2021Zero-Shot Day-Night Domain Adaptation with a Physics Priorcited by 47
  4. 2021SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentationcited by 41
  5. 2021Zero-Shot Learning on 3D Point Cloud Objects and Beyondcited by 38
  6. 2022DUET: Cross-modal Semantic Grounding for Contrastive Zero-shot Learningcited by 33
  7. 2021TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learningcited by 28
  8. 2021Discriminative Region-based Multi-Label Zero-Shot Learningcited by 27
  9. 2022Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Languagecited by 27
  10. 2022VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learningcited by 27
  11. 2022I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classificationcited by 27
  12. 2023Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIPcited by 27
  13. 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
  14. 2024Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Informationcited by 25
  15. 2021Syntactically Guided Generative Embeddings for Zero-Shot Skeleton Action Recognitioncited by 24
  16. 2021Semantic Diversity Learning for Zero-Shot Multi-label Classificationcited by 24
  17. 2021Zero-shot and Few-shot Learning with Knowledge Graphs: A Comprehensive Surveycited by 23
  18. 2023DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotationscited by 22
  19. 2022Towards Unbiased Multi-label Zero-Shot Learning with Pyramid and Semantic Attentioncited by 21
  20. 2021Fine-Grained Zero-Shot Learning with DNA as Side Informationcited by 20
  21. 2021Human Attention in Fine-grained Classificationcited by 20
  22. 2022Hybrid Routing Transformer for Zero-Shot Learningcited by 20
  23. 2023Evolving Semantic Prototype Improves Generative Zero-Shot Learningcited by 20
  24. 2021Generative Multi-Label Zero-Shot Learningcited by 19
  25. 2022Attribute Prototype Network for Any-Shot Learningcited by 19
  26. 2022Temporal and cross-modal attention for audio-visual zero-shot learningcited by 19
  27. 2021Isometric Propagation Network for Generalized Zero-shot Learningcited by 18
  28. 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learningcited by 17
  29. 2021Learning Robust Visual-semantic Mapping for Zero-shot Learningcited by 16
  30. 2023Image-free Classifier Injection for Zero-Shot Classificationcited by 15
  31. 2021Towards Novel Target Discovery Through Open-Set Domain Adaptationcited by 13
  32. 2021Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrievalcited by 13
  33. 2021Mitigating Generation Shifts for Generalized Zero-Shot Learningcited by 13
  34. 2024Low-Resource Vision Challenges for Foundation Modelscited by 13
  35. 2021Hardness Sampling for Self-Training Based Transductive Zero-Shot Learningcited by 12
  36. 2021Multi-Head Self-Attention via Vision Transformer for Zero-Shot Learningcited by 12
  37. 2022GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learningcited by 12
  38. 2022RZCR: Zero-shot Character Recognition via Radical-based Reasoningcited by 12

50 most cited of 164 All 164 (JSON)