2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)最新文献_第3页

Multi-staged deep learning with created coarse and appended fine categories 多阶段深度学习与创建粗和附加细类别

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486461

Reiko Hagawa, Yasunori Ishii, Sotaro Tsukizawa

{"title":"Multi-staged deep learning with created coarse and appended fine categories","authors":"Reiko Hagawa, Yasunori Ishii, Sotaro Tsukizawa","doi":"10.1109/ACPR.2015.7486461","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486461","url":null,"abstract":"This paper proposes a new learning method for Deep Learning based on the concept of a Coarse-to-Fine approach. The Coarse-to-Fine classification improves Deep Learning performance, but it increases network size and presents the problem of close dependence on the accuracy of coarse classification. We tried to avoid this problem by adopting the concept of Curriculum Learning and succeeded in improving the accuracy of Deep Learning. This technique uses learning that employs a single closed image dataset several times in the same network except for the last layer. In this process, coarse labels are given to the images during the pre-training stages and fine labels are given to the same images at the fine-tuning stage. This coarse category pre-training method makes it possible to obtain those features that commonly exist in multiple fine categories. To demonstrate the advantage of this technique, several patterns of a dataset in the quantity of several tens of classes and a single dataset of 100 classes were produced using the ImageNet dataset and compared with the previous technique. The results showed a 5.7% improvement of TOP1 accuracy, with the best case confirmed in the 100-class dataset.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"214 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117347530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

Image set representation and classification with covariate-relation graph 基于协变量关系图的图像集表示与分类

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486603

Zhuqiang Chen, Bo Jiang, Jin Tang, B. Luo

引用次数: 7

High order graphlets for pattern classification 用于模式分类的高阶石墨

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486495

Anjan Dutta, H. Sahbi

{"title":"High order graphlets for pattern classification","authors":"Anjan Dutta, H. Sahbi","doi":"10.1109/ACPR.2015.7486495","DOIUrl":"https://doi.org/10.1109/ACPR.2015.7486495","url":null,"abstract":"Graph-based methods are known to be successful for pattern description and comparison. Their general principle consists in using graphs to model local features as well as their structural relationships and achieving pattern comparison with graph matching. Among these methods, subgraph isomorphism is particularly effective but intractable for general and unconstrained graph structures. In this paper, we introduce an efficient and effective method for graph-based pattern comparison. The main contribution includes a new stochastic search procedure that allows us to efficiently extract, hash and measure the distribution of increasing order subgraphs (a.k.a graphlets) in large graph collections. We consider both low and high order graphlets in order to model local features as well as their complex interactions. These graphlets are partitioned into sets of isomorphic and non-isomorphic subgraphs using well designed hash functions with a low probability of collision; resulting into accurate graph descriptions. When combined with support vector machines, these high order graphlet-based descriptions have positive impact on the performance of pattern comparison and classification as corroborated through experiments on different standard databases.","PeriodicalId":240902,"journal":{"name":"2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128195491","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Towards parameter-less support vector machines 走向无参数支持向量机

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486496

J. Nalepa, Krzysztof Siminski, M. Kawulok

引用次数: 10

Estimation of browsing states in consumer decision processes from eye movements 从眼球运动估计消费者决策过程中的浏览状态

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486543

E. Schaffer, H. Kawashima, T. Matsuyama

引用次数: 0

Efficient cepstrum analysis based UNLM PSF estimation in single blurred image 单幅模糊图像中基于UNLM PSF估计的高效倒谱分析

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486512

Yuta Shimamoto, Qian Chen, Haiyuan Wu, Xiang Ruan, Hikaru Matsumoto

引用次数: 1

Specific changes detection in visible-band VHR images using classification likelihood space 基于分类似然空间的可见光波段VHR图像特异性变化检测

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486530

Feimo Li, Shuxiao Li, Cheng-Fei Zhu, Xiaosong Lan, Hongxing Chang

引用次数: 3

Very deep convolutional neural network based image classification using small training sample size 基于深度卷积神经网络的小样本图像分类

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486599

Shuying Liu, Weihong Deng

引用次数: 643

Sparse autoencoder based spatial pyramid facial feature learning 基于稀疏自编码器的空间金字塔人脸特征学习

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486607

Xiao Ma, Jufu Feng

引用次数: 0

Fast interactive segmentation in stereo images based on multi-scale graph 基于多尺度图的立体图像快速交互式分割

2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2015-11-01 DOI: 10.1109/ACPR.2015.7486505

Wei Ma, Xiaohui Qiu, Luwei Yang, Shuo Liu, Lijuan Duan

引用次数: 0