.png){kind=icon}
返回
W2WNet: A two-module probabilistic Convolutional Neural Network with embedded data cleansing functionality
.png){kind=icon}
OA
AI
DOI：10.1016/j.eswa.2022.119121.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Ideally, Convolutional Neural Networks (CNNs) should be trained with high quality images with minimum noise and correct ground truth labels. Nonetheless, in many real-world scenarios, such high quality is very hard to obtain, and datasets may be affected by any sort of image degradation and mislabelling issues. This negatively impacts the performance of standard CNNs, both during the training and the inference phase. To address this issue we propose Wise2WipedNet (W2WNet), a new two-module Convolutional Neural Network, where a Wise module exploits Bayesian inference to identify and discard spurious images during the training and a Wiped module takes care of the final classification, while broadcasting information on the prediction confidence at inference time. The goodness of our solution is demonstrated on a number of public benchmarks addressing different image classification tasks, as well as on a real-world case study on histological image analysis. Overall, our experiments demonstrate that W2WNet is able to identify image degradation and mislabelling issues both at training and at inference time, with positive impact on the final classification accuracy.
Keyword:
Image classification
Deep learning
Convolutional Neural Networks
Bayesian Convolutional Neural Networks
Data cleansing
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.5
论文数:
2.9W
被引数:
10.2W
机构
引用论文
分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用.png)
PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Effects of Cooling Rate on Impact Toughness of an Ultrahigh-Strength TRIP-Aided Martensitic Steel
PREAI
分享收藏Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis带有噪声标签的深度学习: 探索医学图像分析中的技术和补救措施MEDICAL IMAGE ANALYSISOAAI
MEDICAL IMAGE ANALYSISIF11.8
OAAI分享收藏
查看更多内容