2021 17th International Conference on Machine Vision and Applications (MVA)最新文献_第5页

Distant Bird Detection for Safe Drone Flight and Its Dataset 无人机安全飞行中的远鸟探测及其数据集

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511386

Sanae Fujii, Kazutoshi Akita, N. Ukita

引用次数: 7

Weakly Supervised Domain Adaptation using Super-pixel labeling for Semantic Segmentation 基于超像素标记的弱监督域自适应语义分割

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511365

Masaki Yamazaki, Xingchao Peng, Kuniaki Saito, Ping Hu, Kate Saenko, Y. Taniguchi

引用次数: 0

FBNet: FeedBack-Recursive CNN for Saliency Detection FBNet:用于显著性检测的反馈递归CNN

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511371

Guanqun Ding, Nevrez Imamoglu, Ali Caglayan, M. Murakawa, Ryosuke Nakamura

{"title":"FBNet: FeedBack-Recursive CNN for Saliency Detection","authors":"Guanqun Ding, Nevrez Imamoglu, Ali Caglayan, M. Murakawa, Ryosuke Nakamura","doi":"10.23919/MVA51890.2021.9511371","DOIUrl":"https://doi.org/10.23919/MVA51890.2021.9511371","url":null,"abstract":"Saliency detection research has achieved great progress with the emergence of convolutional neural network (CNN) in recent years. Most deep learning based saliency models mainly adopt the feed-forward CNN architecture with heavy burden of parameters to learn features via bottom-up manner. However, this forward only process may ignore the intrinsic relationship and potential benefits of top-down connections or information flow. To the best of our knowledge, there is not any work to explore the feedback connection especially in a recursive manner for saliency detection. Therefore, we propose and explore a simple, intuitive yet powerful feedback recursive convolutional model (FBNet) for image saliency detection. Specifically, we first select and define a lightweight baseline feed-forward CNN structure (~4.7MB), then the high-level multi-scale saliency features are fed back to the low-level convolutional blocks in a recursive process. Experimental results show that the feedback recursive process is a promising way to improve the performance of the baseline forward CNN model. Besides, despite having relatively few CNN parameters, the proposed FBNet model achieves competitive results on the public saliency detection benchmarks.","PeriodicalId":312481,"journal":{"name":"2021 17th International Conference on Machine Vision and Applications (MVA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117319631","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: 4

Angular Margin Constrained Loss for Automatic Liver Fibrosis Staging 角缘受限损失用于肝纤维化自动分期

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511356

Katsuhiro Nakai, Xu Qiao, X. Han

{"title":"Angular Margin Constrained Loss for Automatic Liver Fibrosis Staging","authors":"Katsuhiro Nakai, Xu Qiao, X. Han","doi":"10.23919/MVA51890.2021.9511356","DOIUrl":"https://doi.org/10.23919/MVA51890.2021.9511356","url":null,"abstract":"Automatic progression staging of liver fibrosis plays very important roles in the direct treatment and the evaluation of prognosis. In clinical site, liver biopsy is popularly used as the gold standard method of liver fibrosis staging, and has obvious drawbacks such as sampling error, heavy burden to patients and high inter-observer variability. Recently, non-invasive techniques as a diagnostic standard have attracted extensive attention. This study exploits a novel deep learning-based liver fibrosis staging framework using non-invasive MRI images. Since there exist large variance in both texture and shape of MRI liver images between patients and subtle distinctness among the progression stages of liver fibrosis, it is a challenge task for accurate progression staging of liver fibrosis. To enhance the discriminative power among the fibrosis stages with subtle difference, this study proposes to integrate angular margin penalty into the conventional softmax loss of the deep learning network, which is expected to enforce extra intra-class compactness and inter-class discrepancy simultaneously. Specifically, we explore the angular margin constrained loss in several classification neural network models such as VGG16, ResNet18, and ResNet50, and further incorporate the between-stage similarity of the training procedure to adaptively adjust the margin for boosting liver fibrosis classification performance. Experiments on the MRI image dataset provided by Shandong University, which includes three progression stages of liver fibrosis: early, middle and last stages, validate that the performance gain with the integration of the angular margin penalty are from 3% to 7% compared to the baseline models: VGG 16, ResNet18, and ResNet50.","PeriodicalId":312481,"journal":{"name":"2021 17th International Conference on Machine Vision and Applications (MVA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131985187","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

Open-set Recognition with Supervised Contrastive Learning 基于监督对比学习的开集识别

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511382

Yuto Kodama, Yinan Wang, Rei Kawakami, T. Naemura

引用次数: 2

Augmenting Discriminative Correlation Filters with Stereo Blob Tracking for Long-Term Tracking of Underwater Animals 基于立体斑点跟踪的增强判别相关滤波器用于水下动物的长期跟踪

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511409

Miaohui Zhang, S. Rock

{"title":"Augmenting Discriminative Correlation Filters with Stereo Blob Tracking for Long-Term Tracking of Underwater Animals","authors":"Miaohui Zhang, S. Rock","doi":"10.23919/MVA51890.2021.9511409","DOIUrl":"https://doi.org/10.23919/MVA51890.2021.9511409","url":null,"abstract":"This paper presents a vision-based model-free longterm tracking algorithm to be used on-board autonomous underwater vehicles (AUVs) for long duration marine animal observation missions. During underwater tracking missions, drifting and losing track of targets after they leave the field of view are two major problems with state-of-the-art tracking algorithms. To achieve the long-term tracking goal, the proposed method gained drift resistance and target re-capturing ability by combining the merits of two mature short-term trackers: stereo blob tracking and discriminative correlation filter (DCF). In our approach, stereo blob tracking acts as complementary supervision to correct drift and to guide DCF to learn target appearances online before any tracking interruptions. The target information learned is then used to help re-capture the target after a tracking failure. In our experiments on field data, compared to running DCF alone, running the proposed augmented tracker increased average bounding box accuracy by 45% and eliminated drift-caused tracking failures. Our tracking algorithm also achieved 86% target re-capturing success.","PeriodicalId":312481,"journal":{"name":"2021 17th International Conference on Machine Vision and Applications (MVA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126787192","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: 0

Information Hiding Using a Coded Aperture as a Key 使用编码孔径作为密钥进行信息隐藏

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511375

Tomoki Minamata, Shoma Ishida, Hiroki Hamasaki, Hiroshi Kawasaki, H. Nagahara, S. Ono

{"title":"Information Hiding Using a Coded Aperture as a Key","authors":"Tomoki Minamata, Shoma Ishida, Hiroki Hamasaki, Hiroshi Kawasaki, H. Nagahara, S. Ono","doi":"10.23919/MVA51890.2021.9511375","DOIUrl":"https://doi.org/10.23919/MVA51890.2021.9511375","url":null,"abstract":"This paper proposes a visual information hiding technique using coded apertures as a key. In general, a watermark embedded as high-frequency components is difficult to extract if it is captured outside of the focal rength and defocus blur occurs. Installation of a coded aperture (CA) into the camera is a simple solution to mitigate the difficulty and several attempts are conducted to make better design for stable extraction. To the contrary, our motivation is to design a specific CA as well as information hiding scheme, where secret information can be decoded only if an image with hidden information is captured with the key aperture whose characteristic is matched with the information hiding scheme. The proposed technique designs the key aperture patterns and information hiding scheme through evolutionary multi-objective optimization so as to minimize the decryption error of a hidden image when using the key aperture while minimizing the accuracy when using other apertures. Experimental results have shown that the proposed information hiding technique was more secure than a password-based system which uses case-insensitive eight alphanumeric characters.","PeriodicalId":312481,"journal":{"name":"2021 17th International Conference on Machine Vision and Applications (MVA)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129654329","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: 0

Illumination Planning for Measuring Per-Pixel Surface Roughness 测量每像素表面粗糙度的照明规划

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511392

Kota Arieda, Takahiro Okabe

引用次数: 1

Shape from shading and polarization constrained by approximate shape 形状从阴影和偏振约束的近似形状

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511399

Wataru Muraoroshi, D. Miyazaki

引用次数: 0

Efficient transfer learning for multi-channel convolutional neural networks 多通道卷积神经网络的高效迁移学习

2021 17th International Conference on Machine Vision and Applications (MVA) Pub Date : 2021-07-25 DOI: 10.23919/MVA51890.2021.9511403

Aloïs de La Comble, K. Prepin

{"title":"Efficient transfer learning for multi-channel convolutional neural networks","authors":"Aloïs de La Comble, K. Prepin","doi":"10.23919/MVA51890.2021.9511403","DOIUrl":"https://doi.org/10.23919/MVA51890.2021.9511403","url":null,"abstract":"Although most convolutional neural networks architectures for computer vision are built to process RGB images, more and more applications complete this information with additional input channels coming from different sensors and data sources. The current techniques for training models on such data, generally leveraging transfer learning, do not take into account the imbalance between RGB channels and additional channels. If no specific strategy is adopted, additional channels are underfitted. We propose to apply channel-wise dropout to inputs to reduce channel underfitting and improve performances. This improvement of performances may be linked to how much new information is brought by additional channels. We propose a method to evaluate this complementarity between additional and RGB channels. We test our approach on three different datasets: a multispectral dataset, a multi-channel PDF dataset and an RGB-D dataset. We find out that results are conclusive on the first two while there is no significant improvement on the last one. In all cases, we observe that additional channels underfitting decreases. We show that this difference of efficiency is linked to complementary between RGB and additional channels.","PeriodicalId":312481,"journal":{"name":"2021 17th International Conference on Machine Vision and Applications (MVA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133046743","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: 5