mlsanityData to 7 Oct 2026

Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification

arXiv 2102.13322 ↗First posted 26 Feb 2021cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

New categories can be discovered by transforming semantic features into synthesized visual features without corresponding training samples in zero-shot image classification. Although significant progress has been made in generating high-quality synthesized visual features using generative adversarial networks, guaranteeing semantic consistency between the semantic features and visual features remains very challenging. In this paper, we propose a novel zero-shot learning approach, GAN-CST, based on class knowledge to visual feature learning to tackle the problem. The approach consists of three parts, class knowledge overlay, semi-supervised learning and triplet loss. It applies class knowledge overlay (CKO) to obtain knowledge not only from the corresponding class but also from other classes that have the knowledge overlay. It ensures that the knowledge-to-visual learning process has adequate information to generate synthesized visual features. The approach also applies a semi-supervised learning process to re-train knowledge-to-visual model. It contributes to reinforcing synthesized visual features generation as well as new category prediction. We tabulate results on a number of benchmark datasets demonstrating that the proposed model delivers superior performance over state-of-the-art approaches.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 33 of its 53 references that are in the map. First posted on arXiv 26 Feb 2021.

Builds on

33 of 53 references.

References · 33

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2015Fast R-CNNcited by 2,930
  3. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  4. 2017Feature Generating Networks for Zero-Shot Learningcited by 257
  5. 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 254
  6. 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
  7. 2014Evaluation of Output Embeddings for Fine-Grained Image Classificationcited by 166
  8. 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
  9. 2016Learning a Deep Embedding Model for Zero-Shot Learningcited by 153
  10. 2013Zero-Shot Learning by Convex Combination of Semantic Embeddingscited by 135
  11. 2016Latent Embeddings for Zero-shot Classificationcited by 129
  12. 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
21 more
  1. 2016Synthesized Classifiers for Zero-Shot Learningcited by 113
  2. 2017A Generative Adversarial Approach for Zero-Shot Learning from Noisy Textscited by 96
  3. 2015Zero-Shot Learning via Semantic Similarity Embeddingcited by 74
  4. 2018The Pros and Cons: Rank-aware Temporal Attention for Skill Determination in Long Videoscited by 68
  5. 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
  6. 2015Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptionscited by 64
  7. 2018Generative Dual Adversarial Network for Generalized Zero-shot Learningcited by 61
  8. 2015Transductive Multi-view Zero-Shot Learningcited by 53
  9. 2017Link the head to the "beak": Zero Shot Learning from Noisy Text Description at Part Precisioncited by 46
  10. 2015Ridge Regression, Hubness, and Zero-Shot Learningcited by 44
  11. 2016Less is more: zero-shot learning from online textual documents with noise suppressioncited by 40
  12. 2014A Unified Perspective on Multi-Domain and Multi-Task Learningcited by 33
  13. 2017Recent Advances in Zero-shot Recognitioncited by 28
  14. 2019Creativity Inspired Zero-Shot Learningcited by 27
  15. 2019CANZSL: Cycle-Consistent Adversarial Networks for Zero-Shot Learning from Natural Languagecited by 23
  16. 2016Multi-Cue Zero-Shot Learning with Strong Supervisioncited by 22
  17. 2017Zero-Shot Learning via Class-Conditioned Deep Generative Modelscited by 21
  18. 2014A Unified Semantic Embedding: Relating Taxonomies and Attributescited by 6
  19. 2021Cross Knowledge-based Generative Zero-Shot Learning Approach with Taxonomy Regularizationcited by 5
  20. 2018Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learningcited by 3
  21. 2019Unified Generator-Classifier for Efficient Zero-Shot Learningcited by 2

Built on by

Not cited yet.