Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00208
T. Pang, Huan Zheng, Yuhui Quan, Hui Ji
Deep denoiser, the deep network for denoising, has been the focus of the recent development on image denoising. In the last few years, there is an increasing interest in developing unsupervised deep denoisers which only call unorganized noisy images without ground truth for training. Nevertheless, the performance of these unsupervised deep denoisers is not competitive to their supervised counterparts. Aiming at developing a more powerful unsupervised deep denoiser, this paper proposed a data augmentation technique, called recorrupted-to-recorrupted (R2R), to address the overfitting caused by the absence of truth images. For each noisy image, we showed that the cost function defined on the noisy/noisy image pairs constructed by the R2R method is statistically equivalent to its supervised counterpart defined on the noisy/truth image pairs. Extensive experiments showed that the proposed R2R method noticeably outperformed existing unsupervised deep denoisers, and is competitive to representative supervised deep denoisers.
{"title":"Recorrupted-to-Recorrupted: Unsupervised Deep Learning for Image Denoising","authors":"T. Pang, Huan Zheng, Yuhui Quan, Hui Ji","doi":"10.1109/CVPR46437.2021.00208","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00208","url":null,"abstract":"Deep denoiser, the deep network for denoising, has been the focus of the recent development on image denoising. In the last few years, there is an increasing interest in developing unsupervised deep denoisers which only call unorganized noisy images without ground truth for training. Nevertheless, the performance of these unsupervised deep denoisers is not competitive to their supervised counterparts. Aiming at developing a more powerful unsupervised deep denoiser, this paper proposed a data augmentation technique, called recorrupted-to-recorrupted (R2R), to address the overfitting caused by the absence of truth images. For each noisy image, we showed that the cost function defined on the noisy/noisy image pairs constructed by the R2R method is statistically equivalent to its supervised counterpart defined on the noisy/truth image pairs. Extensive experiments showed that the proposed R2R method noticeably outperformed existing unsupervised deep denoisers, and is competitive to representative supervised deep denoisers.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129432049","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01459
Tomoki Ichikawa, Matthew Purri, Ryo Kawahara, S. Nobuhara, Kristin J. Dana, K. Nishino
The sky exhibits a unique spatial polarization pattern by scattering the unpolarized sun light. Just like insects use this unique angular pattern to navigate, we use it to map pixels to directions on the sky. That is, we show that the unique polarization pattern encoded in the polarimetric appearance of an object captured under the sky can be decoded to reveal the surface normal at each pixel. We derive a polarimetric reflection model of a diffuse plus mirror surface lit by the sun and a clear sky. This model is used to recover the per-pixel surface normal of an object from a single polarimetric image or from multiple polarimetric images captured under the sky at different times of the day. We experimentally evaluate the accuracy of our shape-from-sky method on a number of real objects of different surface compositions. The results clearly show that this passive approach to fine-geometry recovery that fully leverages the unique illumination made by nature is a viable option for 3D sensing. With the advent of quad-Bayer polarization chips, we believe the implications of our method span a wide range of domains.
{"title":"Shape from Sky: Polarimetric Normal Recovery Under The Sky","authors":"Tomoki Ichikawa, Matthew Purri, Ryo Kawahara, S. Nobuhara, Kristin J. Dana, K. Nishino","doi":"10.1109/CVPR46437.2021.01459","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01459","url":null,"abstract":"The sky exhibits a unique spatial polarization pattern by scattering the unpolarized sun light. Just like insects use this unique angular pattern to navigate, we use it to map pixels to directions on the sky. That is, we show that the unique polarization pattern encoded in the polarimetric appearance of an object captured under the sky can be decoded to reveal the surface normal at each pixel. We derive a polarimetric reflection model of a diffuse plus mirror surface lit by the sun and a clear sky. This model is used to recover the per-pixel surface normal of an object from a single polarimetric image or from multiple polarimetric images captured under the sky at different times of the day. We experimentally evaluate the accuracy of our shape-from-sky method on a number of real objects of different surface compositions. The results clearly show that this passive approach to fine-geometry recovery that fully leverages the unique illumination made by nature is a viable option for 3D sensing. With the advent of quad-Bayer polarization chips, we believe the implications of our method span a wide range of domains.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130506634","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00907
Xin Deng, Hao Wang, Mai Xu, Yichen Guo, Yuhang Song, Li Yang
The omnidirectional images (ODIs) are usually at low-resolution, due to the constraints of collection, storage and transmission. The traditional two-dimensional (2D) image super-resolution methods are not effective for spherical ODIs, because ODIs tend to have non-uniformly distributed pixel density and varying texture complexity across latitudes. In this work, we propose a novel latitude adaptive upscaling network (LAU-Net) for ODI super-resolution, which allows pixels at different latitudes to adopt distinct upscaling factors. Specifically, we introduce a Laplacian multi-level separation architecture to split an ODI into different latitude bands, and hierarchically upscale them with different factors. In addition, we propose a deep reinforcement learning scheme with a latitude adaptive reward, in order to automatically select optimal upscaling factors for different latitude bands. To the best of our knowledge, LAU-Net is the first attempt to consider the latitude difference for ODI super-resolution. Extensive results demonstrate that our LAU-Net significantly advances the super-resolution performance for ODIs. Codes are available at https://github.com/wangh-allen/LAU-Net.
{"title":"LAU-Net: Latitude Adaptive Upscaling Network for Omnidirectional Image Super-resolution","authors":"Xin Deng, Hao Wang, Mai Xu, Yichen Guo, Yuhang Song, Li Yang","doi":"10.1109/CVPR46437.2021.00907","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00907","url":null,"abstract":"The omnidirectional images (ODIs) are usually at low-resolution, due to the constraints of collection, storage and transmission. The traditional two-dimensional (2D) image super-resolution methods are not effective for spherical ODIs, because ODIs tend to have non-uniformly distributed pixel density and varying texture complexity across latitudes. In this work, we propose a novel latitude adaptive upscaling network (LAU-Net) for ODI super-resolution, which allows pixels at different latitudes to adopt distinct upscaling factors. Specifically, we introduce a Laplacian multi-level separation architecture to split an ODI into different latitude bands, and hierarchically upscale them with different factors. In addition, we propose a deep reinforcement learning scheme with a latitude adaptive reward, in order to automatically select optimal upscaling factors for different latitude bands. To the best of our knowledge, LAU-Net is the first attempt to consider the latitude difference for ODI super-resolution. Extensive results demonstrate that our LAU-Net significantly advances the super-resolution performance for ODIs. Codes are available at https://github.com/wangh-allen/LAU-Net.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126797909","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01130
Xingran Zhou, Bo Zhang, Ting Zhang, Pan Zhang, Jianmin Bao, Dong Chen, Zhongfei Zhang, Fang Wen
We present the full-resolution correspondence learning for cross-domain images, which aids image translation. We adopt a hierarchical strategy that uses the correspondence from coarse level to guide the fine levels. At each hierarchy, the correspondence can be efficiently computed via PatchMatch that iteratively leverages the matchings from the neighborhood. Within each PatchMatch iteration, the ConvGRU module is employed to refine the current correspondence considering not only the matchings of larger context but also the historic estimates. The proposed Co-CosNet v2, a GRU-assisted PatchMatch approach, is fully differentiable and highly efficient. When jointly trained with image translation, full-resolution semantic correspondence can be established in an unsupervised manner, which in turn facilitates the exemplar-based image translation. Experiments on diverse translation tasks show that CoCosNet v2 performs considerably better than state-of-the-art literature on producing high-resolution images.
{"title":"CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation","authors":"Xingran Zhou, Bo Zhang, Ting Zhang, Pan Zhang, Jianmin Bao, Dong Chen, Zhongfei Zhang, Fang Wen","doi":"10.1109/CVPR46437.2021.01130","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01130","url":null,"abstract":"We present the full-resolution correspondence learning for cross-domain images, which aids image translation. We adopt a hierarchical strategy that uses the correspondence from coarse level to guide the fine levels. At each hierarchy, the correspondence can be efficiently computed via PatchMatch that iteratively leverages the matchings from the neighborhood. Within each PatchMatch iteration, the ConvGRU module is employed to refine the current correspondence considering not only the matchings of larger context but also the historic estimates. The proposed Co-CosNet v2, a GRU-assisted PatchMatch approach, is fully differentiable and highly efficient. When jointly trained with image translation, full-resolution semantic correspondence can be established in an unsupervised manner, which in turn facilitates the exemplar-based image translation. Experiments on diverse translation tasks show that CoCosNet v2 performs considerably better than state-of-the-art literature on producing high-resolution images.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126984356","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00733
Zhenpei Yang, Erran L. Li, Qi-Xing Huang
Monocular 3D prediction is one of the fundamental problems in 3D vision. Recent deep learning-based approaches have brought us exciting progress on this problem. However, existing approaches have predominantly focused on end-to-end depth and normal predictions, which do not fully utilize the underlying 3D environment’s geometric structures. This paper introduces StruMonoNet, which detects and enforces a planar structure to enhance pixel-wise predictions. StruMonoNet innovates in leveraging a hybrid representation that combines visual feature and a surfel representation for plane prediction. This formulation allows us to combine the power of visual feature learning and the flexibility of geometric representations in incorporating geometric relations. As a result, StruMonoNet can detect relations between planes such as adjacent planes, perpendicular planes, and parallel planes, all of which are beneficial for dense 3D prediction. Experimental results show that StruMonoNet considerably outperforms state-of-the-art approaches on NYUv2 and ScanNet.
{"title":"StruMonoNet: Structure-Aware Monocular 3D Prediction","authors":"Zhenpei Yang, Erran L. Li, Qi-Xing Huang","doi":"10.1109/CVPR46437.2021.00733","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00733","url":null,"abstract":"Monocular 3D prediction is one of the fundamental problems in 3D vision. Recent deep learning-based approaches have brought us exciting progress on this problem. However, existing approaches have predominantly focused on end-to-end depth and normal predictions, which do not fully utilize the underlying 3D environment’s geometric structures. This paper introduces StruMonoNet, which detects and enforces a planar structure to enhance pixel-wise predictions. StruMonoNet innovates in leveraging a hybrid representation that combines visual feature and a surfel representation for plane prediction. This formulation allows us to combine the power of visual feature learning and the flexibility of geometric representations in incorporating geometric relations. As a result, StruMonoNet can detect relations between planes such as adjacent planes, perpendicular planes, and parallel planes, all of which are beneficial for dense 3D prediction. Experimental results show that StruMonoNet considerably outperforms state-of-the-art approaches on NYUv2 and ScanNet.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123805986","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}
Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However, most domain adaptation methods are only restricted to single-source-single-target pair, and can not be directly extended to multiple target domains. In this work, we propose a collaborative learning framework to achieve unsupervised multi-target domain adaptation. An unsupervised domain adaptation expert model is first trained for each source-target pair and is further encouraged to collaborate with each other through a bridge built between different target domains. These expert models are further improved by adding the regularization of making the consistent pixel-wise prediction for each sample with the same structured context. To obtain a single model that works across multiple target domains, we propose to simultaneously learn a student model which is trained to not only imitate the output of each expert on the corresponding target domain, but also to pull different expert close to each other with regularization on their weights. Extensive experiments demonstrate that the proposed method can effectively exploit rich structured information contained in both labeled source domain and multiple unlabeled target domains. Not only does it perform well across multiple target domains but also performs favorably against state-of-the-art unsupervised domain adaptation methods specially trained on a single source-target pair. Code is available at https://github.com/junpan19/MTDA.
{"title":"Multi-Target Domain Adaptation with Collaborative Consistency Learning","authors":"Takashi Isobe, Xu Jia, Shuaijun Chen, Jianzhong He, Yongjie Shi, Jian-zhuo Liu, Huchuan Lu, Shengjin Wang","doi":"10.1109/CVPR46437.2021.00809","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00809","url":null,"abstract":"Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However, most domain adaptation methods are only restricted to single-source-single-target pair, and can not be directly extended to multiple target domains. In this work, we propose a collaborative learning framework to achieve unsupervised multi-target domain adaptation. An unsupervised domain adaptation expert model is first trained for each source-target pair and is further encouraged to collaborate with each other through a bridge built between different target domains. These expert models are further improved by adding the regularization of making the consistent pixel-wise prediction for each sample with the same structured context. To obtain a single model that works across multiple target domains, we propose to simultaneously learn a student model which is trained to not only imitate the output of each expert on the corresponding target domain, but also to pull different expert close to each other with regularization on their weights. Extensive experiments demonstrate that the proposed method can effectively exploit rich structured information contained in both labeled source domain and multiple unlabeled target domains. Not only does it perform well across multiple target domains but also performs favorably against state-of-the-art unsupervised domain adaptation methods specially trained on a single source-target pair. Code is available at https://github.com/junpan19/MTDA.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124224244","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00920
Wenzhao Zheng, Chengkun Wang, Jiwen Lu, Jie Zhou
In this paper, we propose a deep compositional metric learning (DCML) framework for effective and generalizable similarity measurement between images. Conventional deep metric learning methods minimize a discriminative loss to enlarge interclass distances while suppressing intraclass variations, which might lead to inferior generalization performance since samples even from the same class may present diverse characteristics. This motivates the adoption of the ensemble technique to learn a number of sub-embeddings using different and diverse subtasks. However, most subtasks impose weaker or contradictory constraints, which essentially sacrifices the discrimination ability of each sub-embedding to improve the generalization ability of their combination. To achieve a better generalization ability without compromising, we propose to separate the sub-embeddings from direct supervisions from the subtasks and apply the losses on different composites of the sub-embeddings. We employ a set of learnable compositors to combine the sub-embeddings and use a self-reinforced loss to train the compositors, which serve as relays to distribute the diverse training signals to avoid destroying the discrimination ability. Experimental results on the CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate the superior performance of our framework.1
{"title":"Deep Compositional Metric Learning","authors":"Wenzhao Zheng, Chengkun Wang, Jiwen Lu, Jie Zhou","doi":"10.1109/CVPR46437.2021.00920","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00920","url":null,"abstract":"In this paper, we propose a deep compositional metric learning (DCML) framework for effective and generalizable similarity measurement between images. Conventional deep metric learning methods minimize a discriminative loss to enlarge interclass distances while suppressing intraclass variations, which might lead to inferior generalization performance since samples even from the same class may present diverse characteristics. This motivates the adoption of the ensemble technique to learn a number of sub-embeddings using different and diverse subtasks. However, most subtasks impose weaker or contradictory constraints, which essentially sacrifices the discrimination ability of each sub-embedding to improve the generalization ability of their combination. To achieve a better generalization ability without compromising, we propose to separate the sub-embeddings from direct supervisions from the subtasks and apply the losses on different composites of the sub-embeddings. We employ a set of learnable compositors to combine the sub-embeddings and use a self-reinforced loss to train the compositors, which serve as relays to distribute the diverse training signals to avoid destroying the discrimination ability. Experimental results on the CUB-200-2011, Cars196, and Stanford Online Products datasets demonstrate the superior performance of our framework.1","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121563167","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01650
Xu Yang, Cheng Deng, Zhiyuan Dang, Kun-Juan Wei, Junchi Yan
Graph convolution networks (GCNs) are a powerful deep learning approach and have been successfully applied to representation learning on graphs in a variety of real-world applications. Despite their success, two fundamental weaknesses of GCNs limit their ability to represent graph-structured data: poor performance when labeled data are severely scarce and indistinguishable features when more layers are stacked. In this paper, we propose a simple yet effective Self-Supervised Semantic Alignment Graph Convolution Network (SelfSAGCN), which consists of two crux techniques: Identity Aggregation and Semantic Alignment, to overcome these weaknesses. The behind basic idea is the node features in the same class but learned from semantic and graph structural aspects respectively, are expected to be mapped nearby. Specifically, the Identity Aggregation is applied to extract semantic features from labeled nodes, the Semantic Alignment is utilized to align node features obtained from different aspects using the class central similarity. In this way, the over-smoothing phenomenon is alleviated, while the similarities between the unlabeled features and labeled ones from the same class are enhanced. Experimental results on five popular datasets show that the proposed SelfSAGCN outperforms state-of-the-art methods on various classification tasks.
{"title":"Self-SAGCN: Self-Supervised Semantic Alignment for Graph Convolution Network","authors":"Xu Yang, Cheng Deng, Zhiyuan Dang, Kun-Juan Wei, Junchi Yan","doi":"10.1109/CVPR46437.2021.01650","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01650","url":null,"abstract":"Graph convolution networks (GCNs) are a powerful deep learning approach and have been successfully applied to representation learning on graphs in a variety of real-world applications. Despite their success, two fundamental weaknesses of GCNs limit their ability to represent graph-structured data: poor performance when labeled data are severely scarce and indistinguishable features when more layers are stacked. In this paper, we propose a simple yet effective Self-Supervised Semantic Alignment Graph Convolution Network (SelfSAGCN), which consists of two crux techniques: Identity Aggregation and Semantic Alignment, to overcome these weaknesses. The behind basic idea is the node features in the same class but learned from semantic and graph structural aspects respectively, are expected to be mapped nearby. Specifically, the Identity Aggregation is applied to extract semantic features from labeled nodes, the Semantic Alignment is utilized to align node features obtained from different aspects using the class central similarity. In this way, the over-smoothing phenomenon is alleviated, while the similarities between the unlabeled features and labeled ones from the same class are enhanced. Experimental results on five popular datasets show that the proposed SelfSAGCN outperforms state-of-the-art methods on various classification tasks.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127704018","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.01228
Jiexi Yan, Lei Luo, Cheng Deng, Heng Huang
Learning feature embedding directly from images without any human supervision is a very challenging and essential task in the field of computer vision and machine learning. Following the paradigm in supervised manner, most existing unsupervised metric learning approaches mainly focus on binary similarity in Euclidean space. However, these methods cannot achieve promising performance in many practical applications, where the manual information is lacking and data exhibits non-Euclidean latent anatomy. To address this limitation, we propose an Unsupervised Hyperbolic Metric Learning method with Hierarchical Similarity. It considers the natural hierarchies of data by taking advantage of Hyperbolic metric learning and hierarchical clustering, which can effectively excavate richer similarity information beyond binary in modeling. More importantly, we design a new loss function to capture the hierarchical similarity among samples to enhance the stability of the proposed method. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current unsupervised deep metric learning approaches.
{"title":"Unsupervised Hyperbolic Metric Learning","authors":"Jiexi Yan, Lei Luo, Cheng Deng, Heng Huang","doi":"10.1109/CVPR46437.2021.01228","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.01228","url":null,"abstract":"Learning feature embedding directly from images without any human supervision is a very challenging and essential task in the field of computer vision and machine learning. Following the paradigm in supervised manner, most existing unsupervised metric learning approaches mainly focus on binary similarity in Euclidean space. However, these methods cannot achieve promising performance in many practical applications, where the manual information is lacking and data exhibits non-Euclidean latent anatomy. To address this limitation, we propose an Unsupervised Hyperbolic Metric Learning method with Hierarchical Similarity. It considers the natural hierarchies of data by taking advantage of Hyperbolic metric learning and hierarchical clustering, which can effectively excavate richer similarity information beyond binary in modeling. More importantly, we design a new loss function to capture the hierarchical similarity among samples to enhance the stability of the proposed method. Extensive experimental results on benchmark datasets demonstrate that our method achieves state-of-the-art performance compared with current unsupervised deep metric learning approaches.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127725018","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}
Pub Date : 2021-06-01DOI: 10.1109/CVPR46437.2021.00217
S. Cruz, Will Hutchcroft, Yuguang Li, Naji Khosravan, Ivaylo Boyadzhiev, S. B. Kang
We present Zillow Indoor Dataset (ZInD): A large indoor dataset with 71,474 panoramas from 1,524 real unfurnished homes. ZInD provides annotations of 3D room layouts, 2D and 3D floor plans, panorama location in the floor plan, and locations of windows and doors. The ground truth construction took over 1,500 hours of annotation work. To the best of our knowledge, ZInD is the largest real dataset with layout annotations. A unique property is the room layout data, which follows a real world distribution (cuboid, more general Manhattan, and non-Manhattan layouts) as opposed to the mostly cuboid or Manhattan layouts in current publicly available datasets. Also, the scale and annotations provided are valuable for effective research related to room layout and floor plan analysis. To demonstrate ZInD’s benefits, we benchmark on room layout estimation from single panoramas and multi-view registration.
{"title":"Zillow Indoor Dataset: Annotated Floor Plans With 360° Panoramas and 3D Room Layouts","authors":"S. Cruz, Will Hutchcroft, Yuguang Li, Naji Khosravan, Ivaylo Boyadzhiev, S. B. Kang","doi":"10.1109/CVPR46437.2021.00217","DOIUrl":"https://doi.org/10.1109/CVPR46437.2021.00217","url":null,"abstract":"We present Zillow Indoor Dataset (ZInD): A large indoor dataset with 71,474 panoramas from 1,524 real unfurnished homes. ZInD provides annotations of 3D room layouts, 2D and 3D floor plans, panorama location in the floor plan, and locations of windows and doors. The ground truth construction took over 1,500 hours of annotation work. To the best of our knowledge, ZInD is the largest real dataset with layout annotations. A unique property is the room layout data, which follows a real world distribution (cuboid, more general Manhattan, and non-Manhattan layouts) as opposed to the mostly cuboid or Manhattan layouts in current publicly available datasets. Also, the scale and annotations provided are valuable for effective research related to room layout and floor plan analysis. To demonstrate ZInD’s benefits, we benchmark on room layout estimation from single panoramas and multi-view registration.","PeriodicalId":339646,"journal":{"name":"2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127874173","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：