mlsanityData to 14 Oct 2026

Evolving Semantic Prototype Improves Generative Zero-Shot Learning

arXiv 2306.06931 ↗First posted 12 Jun 2023cs.LG cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

In zero-shot learning (ZSL), generative methods synthesize class-related sample features based on predefined semantic prototypes. They advance the ZSL performance by synthesizing unseen class sample features for better training the classifier. We observe that each class's predefined semantic prototype (also referred to as semantic embedding or condition) does not accurately match its real semantic prototype. So the synthesized visual sample features do not faithfully represent the real sample features, limiting the classifier training and existing ZSL performance. In this paper, we formulate this mismatch phenomenon as the visual-semantic domain shift problem. We propose a dynamic semantic prototype evolving (DSP) method to align the empirically predefined semantic prototypes and the real prototypes for class-related feature synthesis. The alignment is learned by refining sample features and semantic prototypes in a unified framework and making the synthesized visual sample features approach real sample features. After alignment, synthesized sample features from unseen classes are closer to the real sample features and benefit DSP to improve existing generative ZSL methods by 8.5%, 8.0%, and 9.7% on the standard CUB, SUN AWA2 datasets, the significant performance improvement indicates that evolving semantic prototype explores a virgin field in ZSL.

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 24 of its 46 references that are in the map. First posted on arXiv 12 Jun 2023.

Builds on

24 of 46 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  3. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  4. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  5. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  6. 2015Label-Embedding for Image Classificationcited by 165
  7. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  8. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  9. 2020A Review of Generalized Zero-Shot Learning Methodscited by 159
  10. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  11. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  12. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
12 more
  1. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  2. 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
  3. 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
  4. 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
  5. 2021TransZero: Attribute-guided Transformer for Zero-Shot Learningcited by 54
  6. 2015Transductive Multi-view Zero-Shot Learningcited by 53
  7. 2020Invertible Zero-Shot Recognition Flowscited by 48
  8. 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
  9. 2019Transductive Zero-Shot Learning with Visual Structure Constraintcited by 36
  10. 2021TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learningcited by 28
  11. 2022I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classificationcited by 27
  12. 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 9; 2026: 3.

20 papers.

Sort:

By area:

  1. 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learningcited by 17
  2. 2024Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learningcited by 16
  3. 2024ZeroDiff: Solidified Visual-Semantic Correlation in Zero-Shot Learningcited by 10
  4. 2023EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learningcited by 6
  5. 2025Interpretable Zero-Shot Learning with Locally-Aligned Vision-Language Modelcited by 6
  6. 2025GenZSL: Generative Zero-Shot Learning Via Inductive Variational Autoencodercited by 5
  7. 2024Adapting Large Multimodal Models to Distribution Shifts: The Role of In-Context Learningcited by 4
  8. 2024Encoding Semantic Priors into the Weights of Implicit Neural Representationcited by 3
  9. 2024PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learningcited by 3
  10. 2024Visual-Semantic Graph Matching Net for Zero-Shot Learningcited by 3
  11. 2025RoHyDR: Robust Hybrid Diffusion Recovery for Incomplete Multimodal Emotion Recognitioncited by 3
  12. 2025MADS: Multi-Attribute Document Supervision for Zero-Shot Image Classificationcited by 2
8 more
  1. 2025Interpretable Zero-shot Learning with Infinite Class Conceptscited by 1
  2. 2025Characterizing Nonlinear Dynamics via Smooth Prototype Equivalencescited by 0
  3. 2025Class Similarity-Based Multimodal Classification under Heterogeneous Category Setscited by 0
  4. 2025Prototype-Guided Curriculum Learning for Zero-Shot Learningcited by 0
  5. 2025Fine-Grained Zero-Shot Learning with Attribute-Centric Representationscited by 0
  6. 2026ZeroDiff++: Substantial Unseen Visual-semantic Correlation in Zero-shot Learningcited by 0
  7. 2026Learning Adaptive and Visually Aligned Conditions for Generative Zero-Shot Learningcited by 0
  8. 2026Incentivizing Generative Zero-Shot Learning via Outcome-Reward Reinforcement Learning with Visual Cuescited by 0