mlsanityData to 7 Oct 2026

Bias-Eliminated Semantic Refinement for Any-Shot Learning

arXiv 2202.04827 ↗First posted 10 Feb 2022cs.CV cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

When training samples are scarce, the semantic embedding technique, ie, describing class labels with attributes, provides a condition to generate visual features for unseen objects by transferring the knowledge from seen objects. However, semantic descriptions are usually obtained in an external paradigm, such as manual annotation, resulting in weak consistency between descriptions and visual features. In this paper, we refine the coarse-grained semantic description for any-shot learning tasks, ie, zero-shot learning (ZSL), generalized zero-shot learning (GZSL), and few-shot learning (FSL). A new model, namely, the semantic refinement Wasserstein generative adversarial network (SRWGAN) model, is designed with the proposed multihead representation and hierarchical alignment techniques. Unlike conventional methods, semantic refinement is performed with the aim of identifying a bias-eliminated condition for disjoint-class feature generation and is applicable in both inductive and transductive settings. We extensively evaluate model performance on six benchmark datasets and observe state-of-the-art results for any-shot learning; eg, we obtain 70.2% harmonic accuracy for the Caltech UCSD Birds (CUB) dataset and 82.2% harmonic accuracy for the Oxford Flowers (FLO) dataset in the standard GZSL setting. Various visualizations are also provided to show the bias-eliminated generation of SRWGAN. Our code is available.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 46 of its 83 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

46 of 83 references.

References · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  6. 2016Matching Networks for One Shot Learningcited by 2,246
  7. 2017Wasserstein GANcited by 635
  8. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  9. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  10. 2015Adversarial Autoencoderscited by 359
  11. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  12. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
34 more
  1. 2015Generative Moment Matching Networkscited by 252
  2. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  3. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  4. 2016Learning Deep Representations of Fine-grained Visual Descriptionscited by 182
  5. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  6. 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
  7. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  8. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
  9. 2013Generalized Denoising Auto-Encoders as Generative Modelscited by 113
  10. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  11. 2018Variational Discriminator Bottleneck: Improving Imitation Learning, Inverse RL, and GANs by Constraining Information Flowcited by 103
  12. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  13. 2019Leveraging the Invariant Side of Generative Zero-Shot Learningcited by 83
  14. 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
  15. 2014PCANet: A Simple Deep Learning Baseline for Image Classification?cited by 70
  16. 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
  17. 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
  18. 2018Generative Dual Adversarial Network for Generalized Zero-shot Learningcited by 61
  19. 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
  20. 2015Transductive Multi-view Zero-Shot Learningcited by 53
  21. 2020Invertible Zero-Shot Recognition Flowscited by 48
  22. 2018Transductive Unbiased Embedding for Zero-Shot Learningcited by 44
  23. 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
  24. 2017A Simple Exponential Family Framework for Zero-Shot Learningcited by 38
  25. 2020Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognitioncited by 34
  26. 2017A Unified approach for Conventional Zero-shot, Generalized Zero-shot and Few-shot Learningcited by 28
  27. 2018Progressive Ensemble Networks for Zero-Shot Recognitioncited by 23
  28. 2017Zero-Shot Learning via Class-Conditioned Deep Generative Modelscited by 21
  29. 2018Attribute-Guided Network for Cross-Modal Zero-Shot Hashingcited by 10
  30. 2019TGG: Transferable Graph Generation for Zero-shot and Few-shot Learningcited by 10
  31. 2020Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Featurecited by 10
  32. 2021Zero Shot on the Cold-Start Problem: Model-Agnostic Interest Learning for Recommender Systemscited by 6
  33. 2016Zero-Shot Learning posed as a Missing Data Problemcited by 3
  34. 2017Nonparametric Inference for Auto-Encoding Variational Bayescited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023Cross-Video Contextual Knowledge Exploration and Exploitation for Ambiguity Reduction in Weakly Supervised Temporal Action Localizationcited by 4
  2. 2024Enabling Generalized Zero-shot Learning Towards Unseen Domains by Intrinsic Learning from Redundant LLM Semanticscited by 0