• Home
  • Search
  • Co-GZSL: Feature Contrastive Optimization for Generalized Zero-Shot Learning
  • Cite Icon5
  • https://doi.org/10.1007/s11063-024-11557-5Copy DOI Icon

Co-GZSL: Feature Contrastive Optimization for Generalized Zero-Shot Learning

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Generalized Zero-Shot Learning (GZSL) learns from only labeled seen classes during training but discriminates both seen and unseen classes during testing. In GZSL tasks, most of the existing methods commonly utilize visual and semantic features for training. Due to the lack of visual features for unseen classes, recent works generate real-like visual features by using semantic features. However, the synthesized features in the original feature space lack discriminative information. It is important that the synthesized visual features should be similar to the ones in the same class, but different from the other classes. One way to solve this problem is to introduce the embedding space after generating visual features. Following this situation, the embedded features from the embedding space can be inconsistent with the original semantic features. For another way, some recent methods constrain the representation by reconstructing the semantic features using the original visual features and the synthesized visual features. In this paper, we propose a hybrid GZSL model, named feature Contrastive optimization for GZSL (Co-GZSL), to reconstruct the semantic features from the embedded features, which ensures that the embedded features are close to the original semantic features indirectly by comparing reconstructed semantic features with original semantic features. In addition, to settle the problem that the synthesized features lack discrimination and semantic consistency, we introduce a Feature Contrastive Optimization Module (FCOM) and jointly utilize contrastive and semantic cycle-consistency losses in the FCOM to strengthen the intra-class compactness and the inter-class separability and to encourage the model to generate semantically consistent and discriminative visual features. By combining the generative module, the embedding module, and the FCOM, we achieve Co-GZSL. We evaluate the proposed Co-GZSL model on four benchmarks, and the experimental results indicate that our model is superior over current methods. Code is available at: https://github.com/zhanzhuxi/Co-GZSL.

Loading PDF

Similar Papers
  • Research Article
  • Citations7

Open zero-shot learning via asymmetric VAE with dissimilarity space

  • Jul 20, 2023
  • Information Sciences
  • Zhibo Zhai +2
  • Conference Article
  • Citations70

En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning

  • Jun 01, 2022
  • Xia Kong +7
  • Research Article
  • Citations36

A Discriminative Cross-Aligned Variational Autoencoder for Zero-Shot Learning.

  • Jun 01, 2023
  • IEEE Transactions on Cybernetics
  • Yang Liu +3
  • Research Article
  • Citations10

Dual Projective Zero-Shot Learning Using Text Descriptions

  • Jan 05, 2023
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Yunbo Rao +4
  • PDF
  • Research Article
  • Citations13

Cooperative Coupled Generative Networks for Generalized Zero-Shot Learning

  • Jan 01, 2020
  • IEEE Access
  • Liang Sun +3
  • Conference Article
  • Citations118

Semantics Disentangling for Generalized Zero-Shot Learning

  • Oct 01, 2021
  • Zhi Chen +6
  • Research Article
  • Citations35

Generative Mixup Networks for Zero-Shot Learning.

  • Mar 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Bingrong Xu +3
  • Report Series

From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process

  • Oct 29, 2018
  • EasyChair preprint
  • Yannick Le Cacheux +2
  • Conference Article
  • Citations16

VS-Boost: Boosting Visual-Semantic Association for Generalized Zero-Shot Learning

  • Aug 01, 2023
  • Xiaofan Li +6
  • Book Chapter
  • Citations71

Multi-modal Text Recognition Networks: Interactive Enhancements Between Visual and Semantic Features

  • Jan 01, 2022
  • Byeonghu Na +2
  • Research Article
  • Citations18

GAN-MVAE: A discriminative latent feature generation framework for generalized zero-shot learning

  • Mar 01, 2022
  • Pattern Recognition Letters
  • Peirong Ma +3
  • Research Article
  • Citations49

Zero-Shot Learning via Robust Latent Representation and Manifold Regularization.

  • Nov 16, 2018
  • IEEE Transactions on Image Processing
  • Min Meng +1
  • Conference Article

Structure-Preserving and Redundancy-Free Features Refinement for Generalized Zero-Shot Learning

  • Jun 04, 2023
  • Jian Ni +1
  • Research Article
  • Citations9

Hierarchical visual-semantic interaction for scene text recognition

  • Oct 18, 2023
  • Information Fusion
  • Liang Diao +4
  • Research Article
  • Citations12

Contrastive semantic disentanglement in latent space for generalized zero-shot learning

  • Sep 30, 2022
  • Knowledge-Based Systems
  • Wentao Fan +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.