A review of generalized zero-shot learning methods

F Pourpanah, M Abdar, Y Luo, X Zhou… - IEEE transactions on …, 2022‏ - ieeexplore.ieee.org
Generalized zero-shot learning (GZSL) aims to train a model for classifying data samples
under the condition that some output classes are unknown during supervised learning. To …

Generalized zero-shot learning via over-complete distribution

R Keshari, R Singh, M Vatsa - Proceedings of the IEEE/CVF …, 2020‏ - openaccess.thecvf.com
A well trained and generalized deep neural network (DNN) should be robust to both seen
and unseen classes. However, the performance of most of the existing supervised DNN …

Adaptive confidence smoothing for generalized zero-shot learning

Y Atzmon, G Chechik - … of the IEEE/CVF Conference on …, 2019‏ - openaccess.thecvf.com
Generalized zero-shot learning (GZSL) is the problem of learning a classifier where some
classes have samples and others are learned from side information, like semantic attributes …

Dual progressive prototype network for generalized zero-shot learning

C Wang, S Min, X Chen, X Sun… - Advances in Neural …, 2021‏ - proceedings.neurips.cc
Abstract Generalized Zero-Shot Learning (GZSL) aims to recognize new categories with
auxiliary semantic information, eg, category attributes. In this paper, we handle the critical …

Part-object progressive refinement network for zero-shot learning

M Liu, C Zhang, H Bai, Y Zhao - IEEE Transactions on Image …, 2024‏ - ieeexplore.ieee.org
Zero-shot learning (ZSL) recognizes unseen images by sharing semantic knowledge
transferred from seen images, encouraging the investigation of associations between …

Evolving semantic prototype improves generative zero-shot learning

S Chen, W Hou, Z Hong, X Ding… - International …, 2023‏ - proceedings.mlr.press
In zero-shot learning (ZSL), generative methods synthesize class-related sample features
based on predefined semantic prototypes. They advance the ZSL performance by …

Dual adversarial semantics-consistent network for generalized zero-shot learning

J Ni, S Zhang, H **e - Advances in neural information …, 2019‏ - proceedings.neurips.cc
Generalized zero-shot learning (GZSL) is a challenging class of vision and knowledge
transfer problems in which both seen and unseen classes appear during testing. Existing …