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 …

Towards zero-shot learning: A brief review and an attention-based embedding network

GS Xie, Z Zhang, H Xiong, L Shao… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Zero-shot learning (ZSL), an emerging topic in recent years, targets at distinguishing unseen
class images by taking images from seen classes for training the classifier. Existing works …

Referit3d: Neural listeners for fine-grained 3d object identification in real-world scenes

P Achlioptas, A Abdelreheem, F Xia… - Computer Vision–ECCV …, 2020 - Springer
In this work we study the problem of using referential language to identify common objects in
real-world 3D scenes. We focus on a challenging setup where the referred object belongs to …

Region graph embedding network for zero-shot learning

GS Xie, L Liu, F Zhu, F Zhao, Z Zhang, Y Yao… - Computer Vision–ECCV …, 2020 - Springer
Most of the existing Zero-Shot Learning (ZSL) approaches learn direct embeddings from
global features or image parts (regions) to the semantic space, which, however, fail to …

Robust deep alignment network with remote sensing knowledge graph for zero-shot and generalized zero-shot remote sensing image scene classification

Y Li, D Kong, Y Zhang, Y Tan, L Chen - ISPRS Journal of Photogrammetry …, 2021 - Elsevier
Although deep learning has revolutionized remote sensing (RS) image scene classification,
current deep learning-based approaches highly depend on the massive supervision of …

Domain-aware visual bias eliminating for generalized zero-shot learning

S Min, H Yao, H Xie, C Wang… - Proceedings of the …, 2020 - openaccess.thecvf.com
Generalized zero-shot learning aims to recognize images from seen and unseen domains.
Recent methods focus on learning a unified semantic-aligned visual representation to …

Invertible zero-shot recognition flows

Y Shen, J Qin, L Huang, L Liu, F Zhu, L Shao - Computer Vision–ECCV …, 2020 - Springer
Deep generative models have been successfully applied to Zero-Shot Learning (ZSL)
recently. However, the underlying drawbacks of GANs and VAEs (eg, the hardness of …

Learning deep cross-modal embedding networks for zero-shot remote sensing image scene classification

Y Li, Z Zhu, JG Yu, Y Zhang - IEEE Transactions on Geoscience …, 2021 - ieeexplore.ieee.org
Due to its wide applications, remote sensing (RS) image scene classification has attracted
increasing research interest. When each category has a sufficient number of labeled …

Bi-directional distribution alignment for transductive zero-shot learning

Z Wang, Y Hao, T Mu, O Li… - Proceedings of the …, 2023 - openaccess.thecvf.com
It is well-known that zero-shot learning (ZSL) can suffer severely from the problem of domain
shift, where the true and learned data distributions for the unseen classes do not match …

Self-supervised generalized zero shot learning for medical image classification using novel interpretable saliency maps

D Mahapatra, Z Ge, M Reyes - IEEE Transactions on Medical …, 2022 - ieeexplore.ieee.org
In many real world medical image classification settings, access to samples of all disease
classes is not feasible, affecting the robustness of a system expected to have high …