mlsanityData to 7 Oct 2026

Deconstructed Generation-Based Zero-Shot Model

arXiv 2204.11280 ↗First posted 24 Apr 2022cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Recent research on Generalized Zero-Shot Learning (GZSL) has focused primarily on generation-based methods. However, current literature has overlooked the fundamental principles of these methods and has made limited progress in a complex manner. In this paper, we aim to deconstruct the generator-classifier framework and provide guidance for its improvement and extension. We begin by breaking down the generator-learned unseen class distribution into class-level and instance-level distributions. Through our analysis of the role of these two types of distributions in solving the GZSL problem, we generalize the focus of the generation-based approach, emphasizing the importance of (i) attribute generalization in generator learning and (ii) independent classifier learning with partially biased data. We present a simple method based on this analysis that outperforms SotAs on four public GZSL datasets, demonstrating the validity of our deconstruction. Furthermore, our proposed method remains effective even without a generative model, representing a step towards simplifying the generator-classifier structure. Our code is available at urlhttps://github.com/cdb342/DGZ.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 38 of its 61 references that are in the map. First posted on arXiv 24 Apr 2022.

Builds on

38 of 61 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  6. 2013Distributed Representations of Words and Phrases and their Compositionalitycited by 3,462
  7. 2017Improved Training of Wasserstein GANscited by 2,223
  8. 2015Learning Transferable Features with Deep Adaptation Networkscited by 1,323
  9. 2017Wasserstein Auto-Encoderscited by 371
  10. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  11. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  12. 2018Analyzing Inverse Problems with Invertible Neural Networkscited by 239
26 more
  1. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  2. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  3. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  4. 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
  5. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  6. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  7. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  8. 2021Contrastive Embedding for Generalized Zero-Shot Learningcited by 94
  9. 2019Leveraging the Invariant Side of Generative Zero-Shot Learningcited by 83
  10. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  11. 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
  12. 2021Goal-Oriented Gaze Estimation for Zero-Shot Learningcited by 68
  13. 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
  14. 2019Transferable Contrastive Network for Generalized Zero-Shot Learningcited by 64
  15. 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
  16. 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
  17. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
  18. 2021TransZero: Attribute-guided Transformer for Zero-Shot Learningcited by 53
  19. 2020Invertible Zero-Shot Recognition Flowscited by 48
  20. 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
  21. 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
  22. 2020Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognitioncited by 34
  23. 2021Dual Progressive Prototype Network for Generalized Zero-Shot Learningcited by 26
  24. 2021Task Aligned Generative Meta-learning for Zero-shot Learningcited by 19
  25. 2021Isometric Propagation Network for Generalized Zero-shot Learningcited by 18
  26. 2021Semantic Feature Extraction for Generalized Zero-shot Learningcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 2; 2026: 1.

6 papers.

  1. 2023ParsNets: A Parsimonious Orthogonal and Low-Rank Linear Networks for Zero-Shot Learningcited by 4
  2. 2025Visual and Semantic Prompt Collaboration for Generalized Zero-Shot Learningcited by 4
  3. 2022Evolutionary Generalized Zero-Shot Learningcited by 3
  4. 2024Zero-Shot Underwater Gesture Recognitioncited by 0
  5. 2025Class Similarity-Based Multimodal Classification under Heterogeneous Category Setscited by 0
  6. 2026CAST: Closed-form Analytic Semantic Transfer for Zero-Shot Classifier Extensioncited by 0