Sketching out the details: Sketch-based image retrieval using convolutional neural networks with multi-stage regression

Bui Tu; Ribeiro Leonardo; Ponti Moacir; Collomosse John

首页> 外文期刊>Computers & Graphics >Sketching out the details: Sketch-based image retrieval using convolutional neural networks with multi-stage regression

【24h】

Sketching out the details: Sketch-based image retrieval using convolutional neural networks with multi-stage regression

机译：勾勒出细节：使用卷积神经网络进行多阶段回归的基于草图的图像检索

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

We propose and evaluate several deep network architectures for measuring the similarity between sketches and photographs, within the context of the sketch based image retrieval (SBIR) task. We study the ability of our networks to generalize across diverse object categories from limited training data, and explore in detail strategies for weight sharing, pre-processing, data augmentation and dimensionality reduction. In addition to a detailed comparative study of network configurations, we contribute by describing a hybrid multi-stage training network that exploits both contrastive and triplet networks to exceed state of the art performance on several SBIR benchmarks by a significant margin. (C) 2017 Elsevier Ltd. All rights reserved.

机译：在基于草图的图像检索（SBIR）任务的背景下，我们提出并评估了几种用于测量草图与照片之间相似度的深度网络体系结构。我们研究了网络从有限的训练数据中概括各种对象类别的能力，并详细研究了权重共享，预处理，数据增强和降维的策略。除了对网络配置进行详细的比较研究之外，我们还通过描述一种混合多阶段训练网络做出了贡献，该网络利用对比网络和三重态网络，大大超过了几个SBIR基准上的最新性能。（C）2017 Elsevier Ltd.保留所有权利。

著录项

来源
《Computers & Graphics》 |2018年第4期|77-87|共11页
作者
Bui Tu; Ribeiro Leonardo; Ponti Moacir; Collomosse John;
展开▼
作者单位

Univ Surrey, CVSSP, Guildford GU2 7XH, Surrey, England;

Univ Sao Paulo, Inst Math & Comp Sci ICMC, BR-13566590 Sao Carlos, SP, Brazil;

Univ Sao Paulo, Inst Math & Comp Sci ICMC, BR-13566590 Sao Carlos, SP, Brazil;

Univ Surrey, CVSSP, Guildford GU2 7XH, Surrey, England;

展开▼
收录信息美国《科学引文索引》(SCI);美国《工程索引》(EI);
原文格式 PDF
正文语种 eng
中图分类
关键词
Sketch based image retrieval (SBIR); Deep learning; Cross-domain modeling; Compact feature representations; Multi-stage regression; Contrastive and triplet losses;

机译：基于草图的图像检索（SBIR）;深度学习;跨域建模;紧凑的特征表示;多阶段回归;对比度损失和三重态损失;

相似文献

外文文献
中文文献
专利

1. Compact descriptors for sketch-based image retrieval using a triplet loss convolutional neural network [J] . T. Bui, L. Ribeiro, M. Ponti, Computer vision and image understanding . 2017,第NOVa期

机译：使用三重损失卷积神经网络的基于草图的图像检索的紧凑描述符
2. DeepSketch 3 Analyzing deep neural networks features for better sketch recognition and sketch-based image retrieval [J] . Seddati Omar, Dupont Stephane, Mahmoudi Said Multimedia Tools and Applications . 2017,第21期

机译：DeepSketch 3分析深度神经网络功能，以更好地进行草图识别和基于草图的图像检索
3. A Novel Sketch-Based Three-Dimensional Shape Retrieval Method Using Multi-View Convolutional Neural Network [J] . Dianhui Mao, Zhihao Hao Symmetry . 2019,第5期

机译：一种基于多视图卷积神经网络的基于草图的三维形状检索方法
4. Sketch-based image retrieval via Siamese convolutional neural network [C] . Yonggang Qi, Yi-Zhe Song, Honggang Zhang, IEEE International Conference on Image Processing . 2016

机译：通过暹罗卷积神经网络进行基于草图的图像检索
5. Sketch and Learn: a sketch-based game framework for studying images. [D] . Wasson, Rajinder. 2012

机译：素描和学习：用于研究图像的基于素描的游戏框架。
6. Automatic Cephalometric Landmark Identification System Based on the Multi-Stage Convolutional Neural Networks with CBCT Combination Images [O] . Min-Jung Kim, Yi Liu, Song Hee Oh, 2021

机译：基于CBCT组合图像的多级卷积神经网络的自动头部测压识别系统
7. Sketching out the details: Sketch-based image retrieval using convolutional neural networks with multi-stage regression [O] . Tu Bui, Leonardo Ribeiro, Moacir Ponti, 2018

机译：勾勒出详细信息：使用多级回归的卷积神经网络进行素描基础的图像检索

Sketching out the details: Sketch-based image retrieval using convolutional neural networks with multi-stage regression

摘要

著录项

相似文献

相关主题

期刊订阅