• Home
  • Search
  • Transductive Zero-Shot Learning by Decoupled Feature Generation
  • Open Access IconOpen Access
  • Cite Icon7
  • https://doi.org/10.1109/wacv48630.2021.00315Copy DOI Icon

Transductive Zero-Shot Learning by Decoupled Feature Generation

  • Jan 1, 2021
  • Federico Marmoreo +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

In this paper, we address zero-shot learning (ZSL), the problem of recognizing categories for which no labeled visual data are available during training. We focus on the transductive setting, in which unlabelled visual data from unseen classes is available. State-of-the-art paradigms in ZSL typically exploit generative adversarial networks to synthesize visual features from semantic attributes. We posit that the main limitation of these approaches is to adopt a single model to face two problems: 1) generating realistic visual features, and 2) translating semantic attributes into visual cues. Differently, we propose to decouple such tasks, solving them separately. In particular, we train an unconditional generator to solely capture the complexity of the distribution of visual data and we subsequently pair it with a conditional generator devoted to enrich the prior knowledge of the data distribution with the semantic content of the class embeddings. We present a detailed ablation study to dissect the effect of our proposed decoupling approach, while demonstrating its superiority over the related state-of-the-art.

Similar Papers
  • Conference Article
  • Citations4

Notice of Removal: Exploiting Semantic Attributes for Transductive Zero-Shot Learning

  • Jun 04, 2023
  • Zhengbo Wang +3
  • PDF
  • Research Article
  • Citations3

Residual-Prototype Generating Network for Generalized Zero-Shot Learning

  • Oct 01, 2022
  • Mathematics
  • Zeqing Zhang +5
  • Research Article
  • Citations17

Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector

  • Jul 29, 2021
  • Knowledge-Based Systems
  • Bo Liu +2
  • Research Article
  • Citations17

Zero-shot image classification using coupled dictionary embedding

  • Feb 18, 2022
  • Machine Learning with Applications
  • Mohammad Rostami +5
  • Conference Article
  • Citations177

Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective

  • Oct 01, 2019
  • Kai Li +2
  • Research Article
  • Citations40

Zero-shot learning for action recognition using synthesized features

  • Jan 23, 2020
  • Neurocomputing
  • Ashish Mishra +2
  • Conference Article
  • Citations106

Semantically Aligned Bias Reducing Zero Shot Learning

  • Jun 01, 2019
  • Akanksha Paul +2
  • Conference Article
  • Citations15

Transductive Visual-Semantic Embedding for Zero-shot Learning

  • Jun 06, 2017
  • Xing Xu +4
  • Research Article
  • Citations11

Explanatory Object Part Aggregation for Zero-Shot Learning.

  • Feb 01, 2024
  • IEEE transactions on pattern analysis and machine intelligence
  • Xin Chen +6
  • Research Article
  • Citations20

Bidirectional generative transductive zero-shot learning

  • Sep 12, 2020
  • Neural Computing and Applications
  • Xinpeng Li +5
  • Conference Article
  • Citations8

Region Semantically Aligned Network for Zero-Shot Learning

  • Oct 26, 2021
  • Ziyang Wang +4
  • Research Article
  • Citations36

Generative Mixup Networks for Zero-Shot Learning.

  • Mar 01, 2025
  • IEEE transactions on neural networks and learning systems
  • Bingrong Xu +3
  • PDF
  • Research Article

Learning Discriminative Projection With Visual Semantic Alignment for Generalized Zero Shot Learning

  • Jan 01, 2020
  • IEEE Access
  • Pengzhen Du +2
  • Research Article
  • Citations1

Prototype Relaxation With Robust Principal Component Analysis for Zero Shot Learning

  • Jan 01, 2020
  • IEEE Access
  • Yong Ma +3
  • Research Article

IMUZero: Zero-Shot Human Activity Recognition by Language-Based Cross Modality Fusion

  • Dec 02, 2025
  • Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
  • Jie Su +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.