Results 1 to 10 of about 16,806 (262)
Detecting Errors with Zero-Shot Learning [PDF]
Entropy, 2022 Error detection is a critical step in data cleaning. Most traditional error detection methods are based on rules and external information with high cost, especially when dealing with large-scaled data.
Xiaoyu Wu, Ning Wang
doaj +6 more sources
HFM: A Hybrid Feature Model Based on Conditional Auto Encoders for Zero-Shot Learning [PDF]
Journal of Imaging, 2022 Zero-Shot Learning (ZSL) is related to training machine learning models capable of classifying or predicting classes (labels) that are not involved in the training set (unseen classes).
Fadi Al Machot, Mohib Ullah, Habib Ullah
doaj +2 more sources
Composite material surface microscopic defect detection and classification combining diffusion models and zero-shot learning [PDF]
Scientific ReportsThis research aims to address the technical challenges of data scarcity and the identification of unseen defect types in the detection of microscopic defects on the surface of composite materials.
Weijun Fan
doaj +2 more sources
Generalized Zero-Shot Learning for Image Classification—Comparing Performance of Popular Approaches
Information, 2022 There are many areas where conventional supervised machine learning does not work well, for instance, in cases with a large, or systematically increasing, number of countably infinite classes. Zero-shot learning has been proposed to address this.
Elie Saad +7 more
doaj +3 more sources
Prognostication of Unseen Objects using Zero-Shot Learning with a Complete Case Analysis [PDF]
Interdisciplinary Description of Complex Systems, 2022 Generally, for a machine learning model to perform well, the data instances on which the model is being trained have to be relevant to the use case.
Srinivasa L. Chakravarthy +1 more
doaj +1 more source
Lifelong Zero-Shot Learning [PDF]
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020 Zero-Shot Learning (ZSL) handles the problem that some testing classes never appear in training set. Existing ZSL methods are designed for learning from a fixed training set, which do not have the ability to capture and accumulate the knowledge of multiple training sets, causing them infeasible to many real-world applications. In this paper, we propose
Kun Wei, Cheng Deng 0002, Xu Yang 0019
openaire +1 more source
IEEE Transactions on Image Processing, 2023 Accepted to IEEE Transactions on Image Processing (TIP ...
Zihan Ye +4 more
openaire +4 more sources
A Survey Of zero shot detection: Methods and applications
Cognitive Robotics, 2021 Zero shot learning (ZSL) is aim to identify objects whose label is unavailable during training. This learning paradigm makes classifier has the ability to distinguish unseen class. The traditional ZSL method only focuses on the image recognition problems
Chufeng Tan, Xing Xu, Fumin Shen
doaj +1 more source
CoRR, 2022 Considering the increasing concerns about data copyright and privacy issues, we present a novel Absolute Zero-Shot Learning (AZSL) paradigm, i.e., training a classifier with zero real data. The key innovation is to involve a teacher model as the data safeguard to guide the AZSL model training without data leaking. The AZSL model consists of a generator
Rui Gao +8 more
openaire +2 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 +1 more source