mlsanityData to 7 Oct 2026

Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks

arXiv 1712.01928 ↗First posted 5 Dec 2017cs.CVcited by 66

Not on the map. Why?

Abstract (arXiv)

We propose a novel framework called Semantics-Preserving Adversarial Embedding Network (SP-AEN) for zero-shot visual recognition (ZSL), where test images and their classes are both unseen during training. SP-AEN aims to tackle the inherent problem --- semantic loss --- in the prevailing family of embedding-based ZSL, where some semantics would be discarded during training if they are non-discriminative for training classes, but could become critical for recognizing test classes. Specifically, SP-AEN prevents the semantic loss by introducing an independent visual-to-semantic space embedder which disentangles the semantic space into two subspaces for the two arguably conflicting objectives: classification and reconstruction. Through adversarial learning of the two subspaces, SP-AEN can transfer the semantics from the reconstructive subspace to the discriminative one, accomplishing the improved zero-shot recognition of unseen classes. Comparing with prior works, SP-AEN can not only improve classification but also generate photo-realistic images, demonstrating the effectiveness of semantic preservation. On four popular benchmarks: CUB, AWA, SUN and aPY, SP-AEN considerably outperforms other state-of-the-art methods by an absolute performance difference of 12.2%, 9.3%, 4.0%, and 3.6% in terms of harmonic mean values

Key facts. Cited by 66 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 33; 2022: 14; 2023: 12; 2024: 3; 2025: 3; 2026: 1.

66 papers.

Sort:

By area:

  1. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  2. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  3. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  4. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  5. 2023Zero-shot Object Countingcited by 57
  6. 2021Semantics for Robotic Mapping, Perception and Interaction: A Surveycited by 56
  7. 2021TransZero: Attribute-guided Transformer for Zero-Shot Learningcited by 53
  8. 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
  9. 2021Self-Supervised Learning Disentangled Group Representation as Featurecited by 47
  10. 2021SIGN: Spatial-information Incorporated Generative Network for Generalized Zero-shot Semantic Segmentationcited by 41
  11. 2021Transporting Causal Mechanisms for Unsupervised Domain Adaptationcited by 38
  12. 2021Partner-Assisted Learning for Few-Shot Image Classificationcited by 36
38 more
  1. 2021A Survey of Unsupervised Domain Adaptation for Visual Recognitioncited by 31
  2. 2021TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learningcited by 28
  3. 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
  4. 2022Domain Adaptation for Time-Series Classification to Mitigate Covariate Shiftcited by 24
  5. 2023Zero-Shot Learning by Harnessing Adversarial Samplescited by 24
  6. 2021Counterfactual Samples Synthesizing and Training for Robust Visual Question Answeringcited by 22
  7. 2021Emergent Discrete Communication in Semantic Spacescited by 20
  8. 2021Fine-Grained Zero-Shot Learning with DNA as Side Informationcited by 20
  9. 2022Hybrid Routing Transformer for Zero-Shot Learningcited by 20
  10. 2021Task Aligned Generative Meta-learning for Zero-shot Learningcited by 19
  11. 2021Relation-aware Compositional Zero-shot Learning for Attribute-Object Pair Recognitioncited by 19
  12. 2021Learning Robust Visual-semantic Mapping for Zero-shot Learningcited by 16
  13. 2022Domain Adaptation Meets Zero-Shot Learning: An Annotation-Efficient Approach to Multi-Modality Medical Image Segmentationcited by 16
  14. 2021Rectification-based Knowledge Retention for Continual Learningcited by 15
  15. 2021Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learningcited by 12
  16. 2022Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesiscited by 11
  17. 2023Zero-Shot Object Counting with Language-Vision Modelscited by 9
  18. 2021Attribute-Modulated Generative Meta Learning for Zero-Shot Classificationcited by 8
  19. 2021Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentationcited by 7
  20. 2023Bi-directional Distribution Alignment for Transductive Zero-Shot Learningcited by 7
  21. 2024Seeing Beyond Classes: Zero-Shot Grounded Situation Recognition via Language Explainercited by 7
  22. 2022How Robust are Discriminatively Trained Zero-Shot Learning Models?cited by 6
  23. 2021Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularizationcited by 5
  24. 2021Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learningcited by 5
  25. 2021An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learningcited by 4
  26. 2021Learning Aligned Cross-Modal Representation for Generalized Zero-Shot Classificationcited by 4
  27. 2022Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learningcited by 4
  28. 2021Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learningcited by 3
  29. 2023Adapt and Align to Improve Zero-Shot Sketch-Based Image Retrievalcited by 3
  30. 2023Bridging the Projection Gap: Overcoming Projection Bias Through Parameterized Distance Learningcited by 3
  31. 2023Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learningcited by 3
  32. 2024Visual-Semantic Graph Matching Net for Zero-Shot Learningcited by 3
  33. 2022Three-Stream Joint Network for Zero-Shot Sketch-Based Image Retrievalcited by 2
  34. 2022LETS-GZSL: A Latent Embedding Model for Time Series Generalized Zero Shot Learningcited by 2
  35. 2023Retrieval-Augmented Meta Learning for Low-Resource Text Classificationcited by 2
  36. 2021Zero-shot Learning with Deep Neural Networks for Object Recognitioncited by 1
  37. 2021Translational Concept Embedding for Generalized Compositional Zero-shot Learningcited by 1
  38. 2022Semantics-driven Attentive Few-shot Learning over Clean and Noisy Samplescited by 1

50 most cited of 66 All 66 (JSON)