mlsanityData to 7 Oct 2026

Semantic Feature Extraction for Generalized Zero-shot Learning

arXiv 2112.14478 ↗First posted 29 Dec 2021cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Generalized zero-shot learning (GZSL) is a technique to train a deep learning model to identify unseen classes using the attribute. In this paper, we put forth a new GZSL technique that improves the GZSL classification performance greatly. Key idea of the proposed approach, henceforth referred to as semantic feature extraction-based GZSL (SE-GZSL), is to use the semantic feature containing only attribute-related information in learning the relationship between the image and the attribute. In doing so, we can remove the interference, if any, caused by the attribute-irrelevant information contained in the image feature. To train a network extracting the semantic feature, we present two novel loss functions, 1) mutual information-based loss to capture all the attribute-related information in the image feature and 2) similarity-based loss to remove unwanted attribute-irrelevant information. From extensive experiments using various datasets, we show that the proposed SE-GZSL technique outperforms conventional GZSL approaches by a large margin.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 22 of its 34 references that are in the map. First posted on arXiv 29 Dec 2021.

Builds on

22 of 34 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2017Improved Training of Wasserstein GANscited by 2,223
  7. 2019On Mutual Information Maximization for Representation Learningcited by 315
  8. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  9. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  10. 2020CLUB: A Contrastive Log-ratio Upper Bound of Mutual Informationcited by 233
  11. 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
  12. 2015Label-Embedding for Image Classificationcited by 164
10 more
  1. 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
  2. 2016An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wildcited by 146
  3. 2018Multi-modal Cycle-consistent Generalized Zero-Shot Learningcited by 87
  4. 2019Leveraging the Invariant Side of Generative Zero-Shot Learningcited by 83
  5. 2017A Generative Model For Zero Shot Learning Using Conditional Variational Autoencoderscited by 64
  6. 2020Leveraging Seen and Unseen Semantic Relationships for Generative Zero-Shot Learningcited by 64
  7. 2021Semantics Disentangling for Generalized Zero-Shot Learningcited by 56
  8. 2020Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognitioncited by 34
  9. 2021Improving Zero-shot Voice Style Transfer via Disentangled Representation Learningcited by 32
  10. 2019Dual Adversarial Semantics-Consistent Network for Generalized Zero-Shot Learningcited by 20

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 3; 2024: 1; 2025: 2.

7 papers.

  1. 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learningcited by 17
  2. 2023Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learningcited by 7
  3. 2022Deconstructed Generation-Based Zero-Shot Modelcited by 6
  4. 2023Semantic-Preserving Augmentation for Robust Image-Text Retrievalcited by 0
  5. 2023SEER-ZSL: Semantic Encoder-Enhanced Representations for Generalized Zero-Shot Learningcited by 0
  6. 2025Few-Shot Inspired Generative Zero-Shot Learningcited by 0
  7. 2025Fine-Grained Zero-Shot Learning with Attribute-Centric Representationscited by 0