2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第6页

GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation 无监督域自适应的图卷积对抗网络

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00846

Xinhong Ma, Tianzhu Zhang, Changsheng Xu

{"title":"GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation","authors":"Xinhong Ma, Tianzhu Zhang, Changsheng Xu","doi":"10.1109/CVPR.2019.00846","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00846","url":null,"abstract":"To bridge source and target domains for domain adaptation, there are three important types of information including data structure, domain label, and class label. Most existing domain adaptation approaches exploit only one or two types of this information and cannot make them complement and enhance each other. Different from existing methods, we propose an end-to-end Graph Convolutional Adversarial Network (GCAN) for unsupervised domain adaptation by jointly modeling data structure, domain label, and class label in a unified deep framework. The proposed GCAN model enjoys several merits. First, to the best of our knowledge, this is the first work to model the three kinds of information jointly in a deep model for unsupervised domain adaptation. Second, the proposed model has designed three effective alignment mechanisms including structure-aware alignment, domain alignment, and class centroid alignment, which can learn domain-invariant and semantic representations effectively to reduce the domain discrepancy for domain adaptation. Extensive experimental results on five standard benchmarks demonstrate that the proposed GCAN algorithm performs favorably against state-of-the-art unsupervised domain adaptation methods.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"21 1","pages":"8258-8268"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73976495","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: 89

Interactive Image Segmentation via Backpropagating Refinement Scheme 基于反向传播细化方案的交互式图像分割

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00544

Won-Dong Jang, Chang-Su Kim

引用次数: 125

Interpretable and Fine-Grained Visual Explanations for Convolutional Neural Networks 卷积神经网络的可解释性和细粒度视觉解释

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00931

Jörg Wagner, Jan M. Köhler, Tobias Gindele, Leon Hetzel, Jakob Thaddäus Wiedemer, Sven Behnke

引用次数: 99

Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection 对比先验与流体金字塔融合的RGBD显著目标检测

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00405

Jiaxing Zhao, Yang Cao, Deng-Ping Fan, Ming-Ming Cheng, Xuan-Yi Li, Le Zhang

引用次数: 324

ZigZagNet: Fusing Top-Down and Bottom-Up Context for Object Segmentation ZigZagNet:融合自顶向下和自底向上的对象分割上下文

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00767

Di Lin, Dingguo Shen, Siting Shen, Yuanfeng Ji, Dani Lischinski, D. Cohen-Or, Hui Huang

引用次数: 55

L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving L3-Net:基于学习的自动驾驶激光雷达定位

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00655

Weixin Lu, Yao Zhou, Guowei Wan, Shenhua Hou, Shiyu Song

{"title":"L3-Net: Towards Learning Based LiDAR Localization for Autonomous Driving","authors":"Weixin Lu, Yao Zhou, Guowei Wan, Shenhua Hou, Shiyu Song","doi":"10.1109/CVPR.2019.00655","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00655","url":null,"abstract":"We present L3-Net - a novel learning-based LiDAR localization system that achieves centimeter-level localization accuracy, comparable to prior state-of-the-art systems with hand-crafted pipelines. Rather than relying on these hand-crafted modules, we innovatively implement the use of various deep neural network structures to establish a learning-based approach. L3-Net learns local descriptors specifically optimized for matching in different real-world driving scenarios. 3D convolutions over a cost volume built in the solution space significantly boosts the localization accuracy. RNNs are demonstrated to be effective in modeling the vehicle's dynamics, yielding better temporal smoothness and accuracy. We comprehensively validate the effectiveness of our approach using freshly collected datasets. Multiple trials of repetitive data collection over the same road and areas make our dataset ideal for testing localization systems. The SunnyvaleBigLoop sequences, with a year's time interval between the collected mapping and testing data, made it quite challenging, but the low localization error of our method in these datasets demonstrates its maturity for real industrial implementation.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"29 1","pages":"6382-6391"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79760241","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: 203

Sea-Thru: A Method for Removing Water From Underwater Images Sea-Thru:一种从水下图像中去除水的方法

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00178

D. Akkaynak, T. Treibitz

{"title":"Sea-Thru: A Method for Removing Water From Underwater Images","authors":"D. Akkaynak, T. Treibitz","doi":"10.1109/CVPR.2019.00178","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00178","url":null,"abstract":"Robust recovery of lost colors in underwater images remains a challenging problem. We recently showed that this was partly due to the prevalent use of an atmospheric image formation model for underwater images. We proposed a physically accurate model that explicitly showed: 1)~the attenuation coefficient of the signal is not uniform across the scene but depends on object range and reflectance, 2)~the coefficient governing the increase in backscatter with distance differs from the signal attenuation coefficient. Here, we present a method that recovers color with the revised model using RGBD images. The emph{Sea-thru} method first calculates backscatter using the darkest pixels in the image and their known range information. Then, it uses an estimate of the spatially varying illuminant to obtain the range-dependent attenuation coefficient. Using more than 1,100 images from two optically different water bodies, which we make available, we show that our method outperforms those using the atmospheric model. Consistent removal of water will open up large underwater datasets to powerful computer vision and machine learning algorithms, creating exciting opportunities for the future of underwater exploration and conservation.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"410 1","pages":"1682-1691"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79850476","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: 44

Versatile Multiple Choice Learning and Its Application to Vision Computing 多功能选择学习及其在视觉计算中的应用

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00651

Kai Tian, Yi Xu, Shuigeng Zhou, J. Guan

{"title":"Versatile Multiple Choice Learning and Its Application to Vision Computing","authors":"Kai Tian, Yi Xu, Shuigeng Zhou, J. Guan","doi":"10.1109/CVPR.2019.00651","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00651","url":null,"abstract":"Most existing ensemble methods aim to train the underlying embedded models independently and simply aggregate their final outputs via averaging or weighted voting. As many prediction tasks contain uncertainty, most of these ensemble methods just reduce variance of the predictions without considering the collaborations among the ensembles. Different from these ensemble methods, multiple choice learning (MCL) methods exploit the cooperation among all the embedded models to generate multiple diverse hypotheses. In this paper, a new MCL method, called vMCL (the abbreviation of versatile Multiple Choice Learning), is developed to extend the application scenarios of MCL methods by ensembling deep neural networks. Our vMCL method keeps the advantage of existing MCL methods while overcoming their major drawback, thus achieves better performance. The novelty of our vMCL lies in three aspects: (1) a choice network is designed to learn the confidence level of each specialist which can provide the best prediction base on multiple hypotheses; (2) a hinge loss is introduced to alleviate the overconfidence issue in MCL settings; (3) Easy to be implemented and can be trained in an end-to-end manner, which is a very attractive feature for many real-world applications. Experiments on image classification and image segmentation task show that vMCL outperforms the existing state-of-the-art MCL methods.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"6342-6350"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85152112","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: 17

TopNet: Structural Point Cloud Decoder TopNet:结构点云解码器

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00047

Lyne P. Tchapmi, V. Kosaraju, Hamid Rezatofighi, I. Reid, S. Savarese

{"title":"TopNet: Structural Point Cloud Decoder","authors":"Lyne P. Tchapmi, V. Kosaraju, Hamid Rezatofighi, I. Reid, S. Savarese","doi":"10.1109/CVPR.2019.00047","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00047","url":null,"abstract":"3D point cloud generation is of great use for 3D scene modeling and understanding. Real-world 3D object point clouds can be properly described by a collection of low-level and high-level structures such as surfaces, geometric primitives, semantic parts,etc. In fact, there exist many different representations of a 3D object point cloud as a set of point groups. Existing frameworks for point cloud genera-ion either do not consider structure in their proposed solutions, or assume and enforce a specific structure/topology,e.g. a collection of manifolds or surfaces, for the generated point cloud of a 3D object. In this work, we pro-pose a novel decoder that generates a structured point cloud without assuming any specific structure or topology on the underlying point set. Our decoder is softly constrained to generate a point cloud following a hierarchical rooted tree structure. We show that given enough capacity and allowing for redundancies, the proposed decoder is very flexible and able to learn any arbitrary grouping of points including any topology on the point set. We evaluate our decoder on the task of point cloud generation for 3D point cloud shape completion. Combined with encoders from existing frameworks, we show that our proposed decoder significantly outperforms state-of-the-art 3D point cloud completion methods on the Shapenet dataset","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"383-392"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89247692","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: 261

Adapting Object Detectors via Selective Cross-Domain Alignment 通过选择性跨域对齐调整目标检测器

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00078

Xinge Zhu, Jiangmiao Pang, Ceyuan Yang, Jianping Shi, Dahua Lin

{"title":"Adapting Object Detectors via Selective Cross-Domain Alignment","authors":"Xinge Zhu, Jiangmiao Pang, Ceyuan Yang, Jianping Shi, Dahua Lin","doi":"10.1109/CVPR.2019.00078","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00078","url":null,"abstract":"State-of-the-art object detectors are usually trained on public datasets. They often face substantial difficulties when applied to a different domain, where the imaging condition differs significantly and the corresponding annotated data are unavailable (or expensive to acquire). A natural remedy is to adapt the model by aligning the image representations on both domains. This can be achieved, for example, by adversarial learning, and has been shown to be effective in tasks like image classification. However, we found that in object detection, the improvement obtained in this way is quite limited. An important reason is that conventional domain adaptation methods strive to align images as a whole, while object detection, by nature, focuses on local regions that may contain objects of interest. Motivated by this, we propose a novel approach to domain adaption for object detection to handle the issues in ``where to look'' and ``how to align''. Our key idea is to mine the discriminative regions, namely those that are directly pertinent to object detection, and focus on aligning them across both domains. Experiments show that the proposed method performs remarkably better than existing methods with about 4% ~ 6% improvement under various domain-shift scenarios while keeping good scalability.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"59 1","pages":"687-696"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89427884","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: 275