Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition最新文献_第4页

Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping. 用于单面无监督领域映射的几何一致生成对抗网络

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2019-06-01 Epub Date: 2020-01-09 DOI: 10.1109/cvpr.2019.00253

Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Kun Zhang, Dacheng Tao

{"title":"Geometry-Consistent Generative Adversarial Networks for One-Sided Unsupervised Domain Mapping.","authors":"Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Kun Zhang, Dacheng Tao","doi":"10.1109/cvpr.2019.00253","DOIUrl":"10.1109/cvpr.2019.00253","url":null,"abstract":"Unsupervised domain mapping aims to learn a function GXY to translate domain <math><mi>X</mi></math> to <math><mi>Y</mi></math> in the absence of paired examples. Finding the optimal G XY without paired data is an ill-posed problem, so appropriate constraints are required to obtain reasonable solutions. While some prominent constraints such as cycle consistency and distance preservation successfully constrain the solution space, they overlook the special properties of images that simple geometric transformations do not change the image's semantic structure. Based on this special property, we develop a geometry-consistent generative adversarial network (Gc-GAN), which enables one-sided unsupervised domain mapping. GcGAN takes the original image and its counterpart image transformed by a predefined geometric transformation as inputs and generates two images in the new domain coupled with the corresponding geometry-consistency constraint. The geometry-consistency constraint reduces the space of possible solutions while keep the correct solutions in the search space. Quantitative and qualitative comparisons with the baseline (GAN alone) and the state-of-the-art methods including CycleGAN [66] and DistanceGAN [5] demonstrate the effectiveness of our method.","PeriodicalId":74560,"journal":{"name":"Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2019 ","pages":"2422-2431"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7030214/pdf/nihms-1037392.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37658933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Networks for Joint Affine and Non-parametric Image Registration. 用于联合仿射和非参数图像注册的网络

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2019-06-01 Epub Date: 2020-01-09 DOI: 10.1109/cvpr.2019.00435

Zhengyang Shen, Xu Han, Zhenlin Xu, Marc Niethammer

{"title":"Networks for Joint Affine and Non-parametric Image Registration.","authors":"Zhengyang Shen, Xu Han, Zhenlin Xu, Marc Niethammer","doi":"10.1109/cvpr.2019.00435","DOIUrl":"10.1109/cvpr.2019.00435","url":null,"abstract":"We introduce an end-to-end deep-learning framework for 3D medical image registration. In contrast to existing approaches, our framework combines two registration methods: an affine registration and a vector momentum-parameterized stationary velocity field (vSVF) model. Specifically, it consists of three stages. In the first stage, a multi-step affine network predicts affine transform parameters. In the second stage, we use a U-Net-like network to generate a momentum, from which a velocity field can be computed via smoothing. Finally, in the third stage, we employ a self-iterable map-based vSVF component to provide a non-parametric refinement based on the current estimate of the transformation map. Once the model is trained, a registration is completed in one forward pass. To evaluate the performance, we conducted longitudinal and cross-subject experiments on 3D magnetic resonance images (MRI) of the knee of the Osteoarthritis Initiative (OAI) dataset. Results show that our framework achieves comparable performance to state-of-the-art medical image registration approaches, but it is much faster, with a better control of transformation regularity including the ability to produce approximately symmetric transformations, and combining affine as well as non-parametric registration.","PeriodicalId":74560,"journal":{"name":"Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2019 ","pages":"4219-4228"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7286599/pdf/nihms-1033312.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38036232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust Histopathology Image Analysis: to Label or to Synthesize? 强大的组织病理学图像分析：贴标签还是合成？

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2019-06-01 Epub Date: 2020-01-09 DOI: 10.1109/CVPR.2019.00873

Le Hou, Ayush Agarwal, Dimitris Samaras, Tahsin M Kurc, Rajarsi R Gupta, Joel H Saltz

{"title":"Robust Histopathology Image Analysis: to Label or to Synthesize?","authors":"Le Hou, Ayush Agarwal, Dimitris Samaras, Tahsin M Kurc, Rajarsi R Gupta, Joel H Saltz","doi":"10.1109/CVPR.2019.00873","DOIUrl":"10.1109/CVPR.2019.00873","url":null,"abstract":"Detection, segmentation and classification of nuclei are fundamental analysis operations in digital pathology. Existing state-of-the-art approaches demand extensive amount of supervised training data from pathologists and may still perform poorly in images from unseen tissue types. We propose an unsupervised approach for histopathology image segmentation that synthesizes heterogeneous sets of training image patches, of every tissue type. Although our synthetic patches are not always of high quality, we harness the motley crew of generated samples through a generally applicable importance sampling method. This proposed approach, for the first time, re-weighs the training loss over synthetic data so that the ideal (unbiased) generalization loss over the true data distribution is minimized. This enables us to use a random polygon generator to synthesize approximate cellular structures (i.e., nuclear masks) for which no real examples are given in many tissue types, and hence, GAN-based methods are not suited. In addition, we propose a hybrid synthesis pipeline that utilizes textures in real histopathology patches and GAN models, to tackle heterogeneity in tissue textures. Compared with existing state-of-the-art supervised models, our approach generalizes significantly better on cancer types without training data. Even in cancer types with training data, our approach achieves the same performance without supervision cost. We release code and segmentation results on over 5000 Whole Slide Images (WSI) in The Cancer Genome Atlas (TCGA) repository, a dataset that would be orders of magnitude larger than what is available today.","PeriodicalId":74560,"journal":{"name":"Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2019 ","pages":"8533-8542"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8139403/pdf/nihms-1025751.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39010307","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-Object Portion Tracking in 4D Fluorescence Microscopy Imagery with Deep Feature Maps. 利用深度特征图在四维荧光显微成像中进行多目标部分跟踪

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2019-06-01 Epub Date: 2020-04-09 DOI: 10.1109/cvprw.2019.00142

Yang Jiao, Mo Weng, Mei Yang

{"title":"Multi-Object Portion Tracking in 4D Fluorescence Microscopy Imagery with Deep Feature Maps.","authors":"Yang Jiao, Mo Weng, Mei Yang","doi":"10.1109/cvprw.2019.00142","DOIUrl":"10.1109/cvprw.2019.00142","url":null,"abstract":"3D fluorescence microscopy of living organisms has increasingly become an essential and powerful tool in biomedical research and diagnosis. An exploding amount of imaging data has been collected, whereas efficient and effective computational tools to extract information from them are still lagging behind. This is largely due to the challenges in analyzing biological data. Interesting biological structures are not only small, but are often morphologically irregular and highly dynamic. Although tracking cells in live organisms has been studied for years, existing tracking methods for cells are not effective in tracking subcellular structures, such as protein complexes, which feature in continuous morphological changes including split and merge, in addition to fast migration and complex motion. In this paper, we first define the problem of multi-object portion tracking to model the protein object tracking process. A multi-object tracking method with portion matching is proposed based on 3D segmentation results. The proposed method distills deep feature maps from deep networks, then recognizes and matches objects' portions using an extended search. Experimental results confirm that the proposed method achieves 2.96% higher on consistent tracking accuracy and 35.48% higher on event identification accuracy than the state-of-art methods.","PeriodicalId":74560,"journal":{"name":"Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2019 ","pages":"1087-1096"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7304548/pdf/nihms-1043641.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38067872","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Weakly Supervised Learning of Single-Cell Feature Embeddings. 单细胞特征嵌入的弱监督学习

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 Epub Date: 2018-12-17 DOI: 10.1109/CVPR.2018.00970

Juan C Caicedo, Claire McQuin, Allen Goodman, Shantanu Singh, Anne E Carpenter

{"title":"Weakly Supervised Learning of Single-Cell Feature Embeddings.","authors":"Juan C Caicedo, Claire McQuin, Allen Goodman, Shantanu Singh, Anne E Carpenter","doi":"10.1109/CVPR.2018.00970","DOIUrl":"10.1109/CVPR.2018.00970","url":null,"abstract":"We study the problem of learning representations for single cells in microscopy images to discover biological relationships between their experimental conditions. Many new applications in drug discovery and functional genomics require capturing the morphology of individual cells as comprehensively as possible. Deep convolutional neural networks (CNNs) can learn powerful visual representations, but require ground truth for training; this is rarely available in biomedical profiling experiments. While we do not know which experimental treatments produce cells that look alike, we do know that cells exposed to the same experimental treatment should generally look similar. Thus, we explore training CNNs using a weakly supervised approach that uses this information for feature learning. In addition, the training stage is regularized to control for unwanted variations using mixup or RNNs. We conduct experiments on two different datasets; the proposed approach yields single-cell embeddings that are more accurate than the widely adopted classical features, and are competitive with previously proposed transfer learning approaches.","PeriodicalId":74560,"journal":{"name":"Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2018 ","pages":"9309-9318"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6432648/pdf/nihms-1018562.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37271663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Learning Facial Action Units from Web Images with Scalable Weakly Supervised Clustering. 使用可扩展的弱监督聚类从网络图像中学习面部动作单元。

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 Epub Date: 2018-12-17 DOI: 10.1109/CVPR.2018.00223

Kaili Zhao, Wen-Sheng Chu, Aleix M Martinez

{"title":"Learning Facial Action Units from Web Images with Scalable Weakly Supervised Clustering.","authors":"Kaili Zhao, Wen-Sheng Chu, Aleix M Martinez","doi":"10.1109/CVPR.2018.00223","DOIUrl":"10.1109/CVPR.2018.00223","url":null,"abstract":"We present a scalable weakly supervised clustering approach to learn facial action units (AUs) from large, freely available web images. Unlike most existing methods (e.g., CNNs) that rely on fully annotated data, our method exploits web images with inaccurate annotations. Specifically, we derive a weakly-supervised spectral algorithm that learns an embedding space to couple image appearance and semantics. The algorithm has efficient gradient update, and scales up to large quantities of images with a stochastic extension. With the learned embedding space, we adopt rank-order clustering to identify groups of visually and semantically similar images, and re-annotate these groups for training AU classifiers. Evaluation on the 1 millon EmotioNet dataset demonstrates the effectiveness of our approach: (1) our learned annotations reach on average 91.3% agreement with human annotations on 7 common AUs, (2) classifiers trained with re-annotated images perform comparably to, sometimes even better than, its supervised CNN-based counterpart, and (3) our method offers intuitive outlier/noise pruning instead of forcing one annotation to every image. Code is available.","PeriodicalId":74560,"journal":{"name":"Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2018 ","pages":"2090-2099"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6594709/pdf/nihms-995319.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37373174","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Ordinal Regression Network for Monocular Depth Estimation. 用于单目深度估计的深度有序回归网络。

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2018-06-01 Epub Date: 2018-12-17 DOI: 10.1109/CVPR.2018.00214

Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Dacheng Tao

{"title":"Deep Ordinal Regression Network for Monocular Depth Estimation.","authors":"Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, Dacheng Tao","doi":"10.1109/CVPR.2018.00214","DOIUrl":"10.1109/CVPR.2018.00214","url":null,"abstract":"Monocular depth estimation, which plays a crucial role in understanding 3D scene geometry, is an ill-posed problem. Recent methods have gained significant improvement by exploring image-level information and hierarchical features from deep convolutional neural networks (DCNNs). These methods model depth estimation as a regression problem and train the regression networks by minimizing mean squared error, which suffers from slow convergence and unsatisfactory local solutions. Besides, existing depth estimation networks employ repeated spatial pooling operations, resulting in undesirable low-resolution feature maps. To obtain high-resolution depth maps, skip-connections or multilayer deconvolution networks are required, which complicates network training and consumes much more computations. To eliminate or at least largely reduce these problems, we introduce a spacing-increasing discretization (SID) strategy to discretize depth and recast depth network learning as an ordinal regression problem. By training the network using an ordinary regression loss, our method achieves much higher accuracy and faster convergence in synch. Furthermore, we adopt a multi-scale network structure which avoids unnecessary spatial pooling and captures multi-scale information in parallel. The proposed deep ordinal regression network (DORN) achieves state-of-the-art results on three challenging benchmarks, i.e., KITTI [16], Make3D [49], and NYU Depth v2 [41], and outperforms existing methods by a large margin.","PeriodicalId":74560,"journal":{"name":"Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2018 ","pages":"2002-2011"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CVPR.2018.00214","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"37119005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1334

Lightweight Probabilistic Deep Networks 轻量级概率深度网络

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2018-05-29 DOI: 10.1109/CVPR.2018.00355

Jochen Gast, S. Roth

{"title":"Lightweight Probabilistic Deep Networks","authors":"Jochen Gast, S. Roth","doi":"10.1109/CVPR.2018.00355","DOIUrl":"https://doi.org/10.1109/CVPR.2018.00355","url":null,"abstract":"Even though probabilistic treatments of neural networks have a long history, they have not found widespread use in practice. Sampling approaches are often too slow already for simple networks. The size of the inputs and the depth of typical CNN architectures in computer vision only compound this problem. Uncertainty in neural networks has thus been largely ignored in practice, despite the fact that it may provide important information about the reliability of predictions and the inner workings of the network. In this paper, we introduce two lightweight approaches to making supervised learning with probabilistic deep networks practical: First, we suggest probabilistic output layers for classification and regression that require only minimal changes to existing networks. Second, we employ assumed density filtering and show that activation uncertainties can be propagated in a practical fashion through the entire network, again with minor changes. Both probabilistic networks retain the predictive power of the deterministic counterpart, but yield uncertainties that correlate well with the empirical error induced by their predictions. Moreover, the robustness to adversarial examples is significantly increased.","PeriodicalId":74560,"journal":{"name":"Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"1 1","pages":"3369-3378"},"PeriodicalIF":0.0,"publicationDate":"2018-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CVPR.2018.00355","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43877862","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: 154

Representations Based on Zero-Crossing in Scale-Space-M 尺度空间- m中基于过零的表示

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2018-02-06 DOI: 10.1016/b978-0-08-051581-6.50072-6

A. Hummel

引用次数: 165

Online Graph Completion: Multivariate Signal Recovery in Computer Vision. 在线图形补全：计算机视觉中的多变量信号恢复

Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Pub Date : 2017-07-01 Epub Date: 2017-11-09 DOI: 10.1109/CVPR.2017.533

Won Hwa Kim, Mona Jalal, Seongjae Hwang, Sterling C Johnson, Vikas Singh

{"title":"Online Graph Completion: Multivariate Signal Recovery in Computer Vision.","authors":"Won Hwa Kim, Mona Jalal, Seongjae Hwang, Sterling C Johnson, Vikas Singh","doi":"10.1109/CVPR.2017.533","DOIUrl":"10.1109/CVPR.2017.533","url":null,"abstract":"The adoption of \"human-in-the-loop\" paradigms in computer vision and machine learning is leading to various applications where the actual data acquisition (e.g., human supervision) and the underlying inference algorithms are closely interwined. While classical work in active learning provides effective solutions when the learning module involves classification and regression tasks, many practical issues such as partially observed measurements, financial constraints and even additional distributional or structural aspects of the data typically fall outside the scope of this treatment. For instance, with sequential acquisition of partial measurements of data that manifest as a matrix (or tensor), novel strategies for completion (or collaborative filtering) of the remaining entries have only been studied recently. Motivated by vision problems where we seek to annotate a large dataset of images via a crowdsourced platform or alternatively, complement results from a state-of-the-art object detector using human feedback, we study the \"completion\" problem defined on graphs, where requests for additional measurements must be made sequentially. We design the optimization model in the Fourier domain of the graph describing how ideas based on adaptive submodularity provide algorithms that work well in practice. On a large set of images collected from Imgur, we see promising results on images that are otherwise difficult to categorize. We also show applications to an experimental design problem in neuroimaging.","PeriodicalId":74560,"journal":{"name":"Proceedings. IEEE Computer Society Conference on Computer Vision and Pattern Recognition","volume":"2017 ","pages":"5019-5027"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5798491/pdf/nihms914460.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35807727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0