FC^4:基于置信度加权池的全卷积颜色一致性

Yuanming Hu, Baoyuan Wang, Stephen Lin
{"title":"FC^4:基于置信度加权池的全卷积颜色一致性","authors":"Yuanming Hu, Baoyuan Wang, Stephen Lin","doi":"10.1109/CVPR.2017.43","DOIUrl":null,"url":null,"abstract":"Improvements in color constancy have arisen from the use of convolutional neural networks (CNNs). However, the patch-based CNNs that exist for this problem are faced with the issue of estimation ambiguity, where a patch may contain insufficient information to establish a unique or even a limited possible range of illumination colors. Image patches with estimation ambiguity not only appear with great frequency in photographs, but also significantly degrade the quality of network training and inference. To overcome this problem, we present a fully convolutional network architecture in which patches throughout an image can carry different confidence weights according to the value they provide for color constancy estimation. These confidence weights are learned and applied within a novel pooling layer where the local estimates are merged into a global solution. With this formulation, the network is able to determine what to learn and how to pool automatically from color constancy datasets without additional supervision. The proposed network also allows for end-to-end training, and achieves higher efficiency and accuracy. On standard benchmarks, our network outperforms the previous state-of-the-art while achieving 120x greater efficiency.","PeriodicalId":6631,"journal":{"name":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"37 1","pages":"330-339"},"PeriodicalIF":0.0000,"publicationDate":"2017-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"184","resultStr":"{\"title\":\"FC^4: Fully Convolutional Color Constancy with Confidence-Weighted Pooling\",\"authors\":\"Yuanming Hu, Baoyuan Wang, Stephen Lin\",\"doi\":\"10.1109/CVPR.2017.43\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Improvements in color constancy have arisen from the use of convolutional neural networks (CNNs). However, the patch-based CNNs that exist for this problem are faced with the issue of estimation ambiguity, where a patch may contain insufficient information to establish a unique or even a limited possible range of illumination colors. Image patches with estimation ambiguity not only appear with great frequency in photographs, but also significantly degrade the quality of network training and inference. To overcome this problem, we present a fully convolutional network architecture in which patches throughout an image can carry different confidence weights according to the value they provide for color constancy estimation. These confidence weights are learned and applied within a novel pooling layer where the local estimates are merged into a global solution. With this formulation, the network is able to determine what to learn and how to pool automatically from color constancy datasets without additional supervision. The proposed network also allows for end-to-end training, and achieves higher efficiency and accuracy. On standard benchmarks, our network outperforms the previous state-of-the-art while achieving 120x greater efficiency.\",\"PeriodicalId\":6631,\"journal\":{\"name\":\"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)\",\"volume\":\"37 1\",\"pages\":\"330-339\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2017-07-21\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"184\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/CVPR.2017.43\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CVPR.2017.43","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 184

摘要

使用卷积神经网络(cnn)可以改善颜色的稳定性。然而,针对该问题存在的基于patch的cnn面临着估计模糊的问题,其中patch可能包含的信息不足,无法建立唯一甚至有限的可能照明颜色范围。带有估计模糊的图像补丁不仅在照片中出现的频率很高,而且严重降低了网络训练和推理的质量。为了克服这个问题,我们提出了一个全卷积网络架构,其中图像中的补丁可以根据它们提供的颜色常量估计值携带不同的置信度权重。这些置信度权重被学习并应用在一个新的池化层中,在这个池化层中,局部估计被合并到一个全局解决方案中。有了这个公式,网络就能够确定要学习什么,以及如何在没有额外监督的情况下从颜色恒定数据集中自动池化。该网络还允许端到端训练,实现了更高的效率和准确性。在标准基准测试中,我们的网络性能优于以前的最先进的技术,同时实现了120倍的效率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
FC^4: Fully Convolutional Color Constancy with Confidence-Weighted Pooling
Improvements in color constancy have arisen from the use of convolutional neural networks (CNNs). However, the patch-based CNNs that exist for this problem are faced with the issue of estimation ambiguity, where a patch may contain insufficient information to establish a unique or even a limited possible range of illumination colors. Image patches with estimation ambiguity not only appear with great frequency in photographs, but also significantly degrade the quality of network training and inference. To overcome this problem, we present a fully convolutional network architecture in which patches throughout an image can carry different confidence weights according to the value they provide for color constancy estimation. These confidence weights are learned and applied within a novel pooling layer where the local estimates are merged into a global solution. With this formulation, the network is able to determine what to learn and how to pool automatically from color constancy datasets without additional supervision. The proposed network also allows for end-to-end training, and achieves higher efficiency and accuracy. On standard benchmarks, our network outperforms the previous state-of-the-art while achieving 120x greater efficiency.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信