• Home
  • Search
  • Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
  • Open Access IconOpen Access
  • Cite Icon177
  • https://doi.org/10.1109/iccv.2019.00368Copy DOI Icon

Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective

  • Oct 1, 2019
  • Kai Li +2 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Zero-shot learning (ZSL) aims to recognize instances of unseen classes solely based on the semantic descriptions of the classes. Existing algorithms usually formulate it as a semantic-visual correspondence problem, by learning mappings from one feature space to the other. Despite being reasonable, previous approaches essentially discard the highly precious discriminative power of visual features in an implicit way, and thus produce undesirable results. We instead reformulate ZSL as a conditioned visual classification problem, i.e., classifying visual features based on the classifiers learned from the semantic descriptions. With this reformulation, we develop algorithms targeting various ZSL settings: For the conventional setting, we propose to train a deep neural network that directly generates visual feature classifiers from the semantic attributes with an episode-based training scheme; For the generalized setting, we concatenate the learned highly discriminative classifiers for seen classes and the generated classifiers for unseen classes to classify visual features of all classes; For the transductive setting, we exploit unlabeled data to effectively calibrate the classifier generator using a novel learning-without-forgetting self-training mechanism and guide the process by a robust generalized cross-entropy loss. Extensive experiments show that our proposed algorithms significantly outperform state-of-the-art methods by large margins on most benchmark datasets in all the ZSL settings.

Similar Papers
  • PDF
  • Research Article
  • Citations3

Residual-Prototype Generating Network for Generalized Zero-Shot Learning

  • Oct 01, 2022
  • Mathematics
  • Zeqing Zhang +5
  • Conference Article
  • Citations106

Semantically Aligned Bias Reducing Zero Shot Learning

  • Jun 01, 2019
  • Akanksha Paul +2
  • 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
  • Research Article
  • Citations11

Zero-shot learning via visual feature enhancement and dual classifier learning for image recognition

  • May 18, 2023
  • Information Sciences
  • Peng Zhao +4
  • Research Article
  • Citations7

Superclass-aware visual feature disentangling for generalized zero-shot learning

  • Aug 28, 2024
  • Expert Systems With Applications
  • Chang Niu +3
  • Research Article
  • Citations17

Zero-shot image classification using coupled dictionary embedding

  • Feb 18, 2022
  • Machine Learning with Applications
  • Mohammad Rostami +5
  • Research Article
  • Citations78

Attribute Propagation Network for Graph Zero-Shot Learning

  • Apr 03, 2020
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Lu Liu +4
  • Research Article
  • Citations9

A framework to enhance generalization of deep metric learning methods using general discriminative feature learning and class adversarial neural networks

  • Aug 02, 2022
  • Applied Intelligence
  • Karrar Al-Kaabi +2
  • PDF
  • Research Article

Variational Disentangle Zero-Shot Learning

  • Aug 18, 2023
  • Mathematics
  • Jie Su +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
  • Research Article
  • Citations37

Learning adversarial semantic embeddings for zero-shot recognition in open worlds

  • Jan 11, 2024
  • Pattern Recognition
  • Tianqi Li +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
  • Citations14

Modality independent adversarial network for generalized zero shot image classification

  • Nov 21, 2020
  • Neural Networks
  • Haofeng Zhang +4
  • Research Article

Auto‐encode the synthesis pseudo features for generalized zero‐shot learning

  • Sep 03, 2022
  • The Journal of Engineering
  • Lin Wang +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
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.