mlsanityData to 14 Oct 2026

Prototypical Model with Novel Information-theoretic Loss Function for Generalized Zero Shot Learning

arXiv 2112.03134 ↗First posted 6 Dec 2021cs.LG cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Generalized zero shot learning (GZSL) is still a technical challenge of deep learning as it has to recognize both source and target classes without data from target classes. To preserve the semantic relation between source and target classes when only trained with data from source classes, we address the quantification of the knowledge transfer and semantic relation from an information-theoretic viewpoint. To this end, we follow the prototypical model and format the variables of concern as a probability vector. Leveraging on the proposed probability vector representation, the information measurement such as mutual information and entropy, can be effectively evaluated with simple closed forms. We discuss the choice of common embedding space and distance function when using the prototypical model. Then We propose three information-theoretic loss functions for deterministic GZSL model: a mutual information loss to bridge seen data and target classes; an uncertainty-aware entropy constraint loss to prevent overfitting when using seen data to learn the embedding of target classes; a semantic preserving cross entropy loss to preserve the semantic relation when mapping the semantic representations to the common space. Simulation shows that, as a deterministic model, our proposed method obtains state of the art results on GZSL benchmark datasets. We achieve 21%-64% improvements over the baseline model -- deep calibration network (DCN) and for the first time demonstrate a deterministic model can perform as well as generative ones. Moreover, our proposed model is compatible with generative models. Simulation studies show that by incorporating with f-CLSWGAN, we obtain comparable results compared with advanced generative models.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 60 references that are in the map. First posted on arXiv 6 Dec 2021.

Builds on

33 of 60 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,375
  5. 2013Auto-Encoding Variational Bayescited by 4,053
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  7. 2016Matching Networks for One Shot Learningcited by 2,255
  8. 2017Wasserstein GANcited by 639
  9. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 464
  10. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  11. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 255
  12. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
21 more
  1. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  2. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  3. 2015Label-Embedding for Image Classificationcited by 165
  4. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  5. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  6. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  7. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  8. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  9. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  10. 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
  11. 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
  12. 2019Transferable Contrastive Network for Generalized Zero-Shot Learningcited by 64
  13. 2018Generative Dual Adversarial Network for Generalized Zero-shot Learningcited by 61
  14. 2017Learning Robust Visual-Semantic Embeddingscited by 56
  15. 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
  16. 2015Transductive Multi-view Zero-Shot Learningcited by 53
  17. 2020Invertible Zero-Shot Recognition Flowscited by 48
  18. 2015Ridge Regression, Hubness, and Zero-Shot Learningcited by 44
  19. 2018Preserving Semantic Relations for Zero-Shot Learningcited by 35
  20. 2018Towards Effective Deep Embedding for Zero-Shot Learningcited by 19
  21. 2018Zero-Shot Kernel Learningcited by 11

Built on by

Not cited yet.