Results 1 to 10 of about 11,177,407 (275)

Zero-Shot Image Classification Based on a Learnable Deep Metric [PDF]

Sensors, 2021
The supervised model based on deep learning has made great achievements in the field of image classification after training with a large number of labeled samples.
Jingyi Liu, Caijuan Shi, Dongjing Tu, Ze Shi, Yazhi Liu   +4 more
doaj   +8 more sources

CGUN-2A: Deep Graph Convolutional Network via Contrastive Learning for Large-Scale Zero-Shot Image Classification [PDF]

Sensors, 2022
Taxonomy illustrates that natural creatures can be classified with a hierarchy. The connections between species are explicit and objective and can be organized into a knowledge graph (KG).
Liangwei Li, Lin Liu, Xiaohui Du, Xiangzhou Wang, Ziruo Zhang, Jing Zhang, Ping Zhang, Juanxiu Liu   +7 more
doaj   +4 more sources

Embedded Zero-Shot Image Classification Based on Bidirectional Feature Mapping

Applied Sciences
The zero-shot image classification technique aims to explore the semantic information shared between seen and unseen classes through visual features and auxiliary information and, based on this semantic information, to complete the knowledge migration ...
Huadong Sun, Zhibin Zhen, Yinghui Liu, Xu Zhang, Xiaowei Han, Pengyi Zhang   +5 more
doaj   +4 more sources

Underwater Sonar Image Classification with Image Disentanglement Reconstruction and Zero-Shot Learning

Remote Sensing
Sonar is a valuable tool for ocean exploration since it can obtain a wealth of data. With the development of intelligent technology, deep learning has brought new vitality to underwater sonar image classification.
Ye Peng, Houpu Li, Wenwen Zhang, Junhui Zhu, Lei Liu, Guojun Zhai   +5 more
doaj   +4 more sources

Survey of Zero-Shot Image Classification

Jisuanji kexue yu tansuo, 2021
It is time-consuming and laborious to manually label a large number of samples, and samples from some rare classes are difficult to obtain. Therefore, the zero-shot image classification has become a research hotspot in the computer vision field. Firstly,
LIU Jingyi, SHI Caijuan, TU Dongjing, LIU Shuai
doaj   +2 more sources

Zero-shot image classification using coupled dictionary embedding

Machine Learning with Applications, 2022
Zero-shot learning (ZSL) is a framework to classify images that belong to unseen visual classes using their semantic descriptions about the unseen classes. We develop a new ZSL algorithm based on coupled dictionary learning.
Mohammad Rostami, Soheil Kolouri, Zak Murez, Yuri Owechko, Eric Eaton, Kuyngnam Kim   +5 more
doaj   +4 more sources

A Cross-Modal Alignment for Zero-Shot Image Classification

IEEE Access, 2023
Different from major classification methods based on large amounts of annotation data, we introduce a cross-modal alignment for zero-shot image classification.The key is utilizing the query of text attribute learned from the seen classes to guide local ...
Lu Wu, Chenyu Wu, Han Guo, Zhihao Zhao
doaj   +3 more sources

Zero-shot image classification based on class representation learning and attribute embedding learning. [PDF]

PLoS ONE
Zero-shot learning (ZSL) aims to classify unseen classes by leveraging semantic information from seen classes, addressing the challenge of limited labeled data.
Huabo Shen, Xiaodong Sun, Youmin Hu, Changgeng Li, Qinmiao Zhu, Qin Li   +5 more
doaj   +2 more sources

Integrating Adversarial Generative Network with Variational Autoencoders towards Cross-Modal Alignment for Zero-Shot Remote Sensing Image Scene Classification

Remote Sensing, 2022
Remote sensing image scene classification takes image blocks as classification units and predicts their semantic descriptors. Because it is difficult to obtain enough labeled samples for all classes of remote sensing image scenes, zero-shot ...
Suqiang Ma, Chun Liu, Zheng Li, Wei Yang
doaj   +3 more sources

Vision-Language Models for Zero-Shot Classification of Remote Sensing Images

Applied Sciences, 2023
Zero-shot classification presents a challenge since it necessitates a model to categorize images belonging to classes it has not encountered during its training phase.
Mohamad Mahmoud Al Rahhal, Yakoub Bazi, Hebah Elgibreen, Mansour Zuair   +3 more
doaj   +3 more sources