mlsanityData to 7 Oct 2026

End-to-end Generative Zero-shot Learning via Few-shot Learning

arXiv 2102.04379 ↗First posted 8 Feb 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Contemporary state-of-the-art approaches to Zero-Shot Learning (ZSL) train generative nets to synthesize examples conditioned on the provided metadata. Thereafter, classifiers are trained on these synthetic data in a supervised manner. In this work, we introduce Z2FSL, an end-to-end generative ZSL framework that uses such an approach as a backbone and feeds its synthesized output to a Few-Shot Learning (FSL) algorithm. The two modules are trained jointly. Z2FSL solves the ZSL problem with a FSL algorithm, reducing, in effect, ZSL to FSL. A wide class of algorithms can be integrated within our framework. Our experimental results show consistent improvement over several baselines. The proposed method, evaluated across standard benchmarks, shows state-of-the-art or competitive performance in ZSL and Generalized ZSL tasks.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 8 Feb 2021.

Builds on

37 of 56 references.

References · 37

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  7. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  8. 2013Auto-Encoding Variational Bayescited by 3,980
  9. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  10. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  11. 2016Matching Networks for One Shot Learningcited by 2,246
  12. 2017Improved Training of Wasserstein GANscited by 2,223
25 more
  1. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
  2. 2017Wasserstein GANcited by 635
  3. 2016Conditional Image Synthesis With Auxiliary Classifier GANscited by 562
  4. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 536
  5. 2017CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learningcited by 459
  6. 2017Data Augmentation Generative Adversarial Networkscited by 278
  7. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  8. 2019Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderercited by 221
  9. 2018Low-Shot Learning from Imaginary Datacited by 181
  10. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  11. 2015Label-Embedding for Image Classificationcited by 164
  12. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  13. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  14. 2017Semantic Autoencoder for Zero-Shot Learningcited by 133
  15. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  16. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  17. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  18. 2019Leveraging the Invariant Side of Generative Zero-Shot Learningcited by 83
  19. 2018Generative Dual Adversarial Network for Generalized Zero-shot Learningcited by 61
  20. 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
  21. 2013Estimating or Propagating Gradients Through Stochastic Neuronscited by 54
  22. 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
  23. 2016Less is more: zero-shot learning from online textual documents with noise suppressioncited by 40
  24. 2019Creativity Inspired Zero-Shot Learningcited by 27
  25. 2016Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learningcited by 20

Built on by

Not cited yet.