Synthesizing novel views from a 2D image requires to infer 3D structure and project it back to 2D from a new viewpoint. In this paper, we propose an encoder-decoder based generative adversarial network VI-GAN to tackle this problem. Our method is to let the network, after seeing many images of objects belonging to the same category in different views, obtain essential knowledge of intrinsic properties of the objects. To this end, an encoder is designed to extract view-independent feature that characterizes intrinsic properties of the input image, which includes 3D structure, color, texture etc. We also make the decoder hallucinate the image of a novel view based on the extracted feature and an arbitrary user-specific camera pose. Extensive experiments demonstrate that our model can synthesize high-quality images in different views with continuous camera poses, and is general for various applications.
{"title":"View Independent Generative Adversarial Network for Novel View Synthesis","authors":"Xiaogang Xu, Ying-Cong Chen, Jiaya Jia","doi":"10.1109/ICCV.2019.00788","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00788","url":null,"abstract":"Synthesizing novel views from a 2D image requires to infer 3D structure and project it back to 2D from a new viewpoint. In this paper, we propose an encoder-decoder based generative adversarial network VI-GAN to tackle this problem. Our method is to let the network, after seeing many images of objects belonging to the same category in different views, obtain essential knowledge of intrinsic properties of the objects. To this end, an encoder is designed to extract view-independent feature that characterizes intrinsic properties of the input image, which includes 3D structure, color, texture etc. We also make the decoder hallucinate the image of a novel view based on the extracted feature and an arbitrary user-specific camera pose. Extensive experiments demonstrate that our model can synthesize high-quality images in different views with continuous camera poses, and is general for various applications.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"5 1","pages":"7790-7799"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73300554","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}
With excellent representation power for complex data, deep neural networks (DNNs) based approaches are state-of-the-art for ordinal regression problem which aims to classify instances into ordinal categories. However, DNNs are not able to capture uncertainties and produce probabilistic interpretations. As a probabilistic model, Gaussian Processes (GPs) on the other hand offers uncertainty information, which is nonetheless lack of scalability for large datasets. This paper adapts traditional GPs regression for ordinal regression problem by using both conjugate and non-conjugate ordinal likelihood. Based on that, it proposes a deep neural network with a GPs layer on the top, which is trained end-to-end by the stochastic gradient descent method for both neural network parameters and GPs parameters. The parameters in the ordinal likelihood function are learned as neural network parameters so that the proposed framework is able to produce fitted likelihood functions for training sets and make probabilistic predictions for test points. Experimental results on three real-world benchmarks -- image aesthetics rating, historical image grading and age group estimation -- demonstrate that in terms of mean absolute error, the proposed approach outperforms state-of-the-art ordinal regression approaches and provides the confidence for predictions.
{"title":"Probabilistic Deep Ordinal Regression Based on Gaussian Processes","authors":"Yanzhu Liu, Fan Wang, A. Kong","doi":"10.1109/ICCV.2019.00540","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00540","url":null,"abstract":"With excellent representation power for complex data, deep neural networks (DNNs) based approaches are state-of-the-art for ordinal regression problem which aims to classify instances into ordinal categories. However, DNNs are not able to capture uncertainties and produce probabilistic interpretations. As a probabilistic model, Gaussian Processes (GPs) on the other hand offers uncertainty information, which is nonetheless lack of scalability for large datasets. This paper adapts traditional GPs regression for ordinal regression problem by using both conjugate and non-conjugate ordinal likelihood. Based on that, it proposes a deep neural network with a GPs layer on the top, which is trained end-to-end by the stochastic gradient descent method for both neural network parameters and GPs parameters. The parameters in the ordinal likelihood function are learned as neural network parameters so that the proposed framework is able to produce fitted likelihood functions for training sets and make probabilistic predictions for test points. Experimental results on three real-world benchmarks -- image aesthetics rating, historical image grading and age group estimation -- demonstrate that in terms of mean absolute error, the proposed approach outperforms state-of-the-art ordinal regression approaches and provides the confidence for predictions.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"48 1","pages":"5300-5308"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82134279","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}
Huikun Bi, Zhong Fang, Tianlu Mao, Zhaoqi Wang, Z. Deng
Trajectory prediction for objects is challenging and critical for various applications (e.g., autonomous driving, and anomaly detection). Most of the existing methods focus on homogeneous pedestrian trajectories prediction, where pedestrians are treated as particles without size. However, they fall short of handling crowded vehicle-pedestrian-mixed scenes directly since vehicles, limited with kinematics in reality, should be treated as rigid, non-particle objects ideally. In this paper, we tackle this problem using separate LSTMs for heterogeneous vehicles and pedestrians. Specifically, we use an oriented bounding box to represent each vehicle, calculated based on its position and orientation, to denote its kinematic trajectories. We then propose a framework called VP-LSTM to predict the kinematic trajectories of both vehicles and pedestrians simultaneously. In order to evaluate our model, a large dataset containing the trajectories of both vehicles and pedestrians in vehicle-pedestrian-mixed scenes is specially built. Through comparisons between our method with state-of-the-art approaches, we show the effectiveness and advantages of our method on kinematic trajectories prediction in vehicle-pedestrian-mixed scenes.
{"title":"Joint Prediction for Kinematic Trajectories in Vehicle-Pedestrian-Mixed Scenes","authors":"Huikun Bi, Zhong Fang, Tianlu Mao, Zhaoqi Wang, Z. Deng","doi":"10.1109/ICCV.2019.01048","DOIUrl":"https://doi.org/10.1109/ICCV.2019.01048","url":null,"abstract":"Trajectory prediction for objects is challenging and critical for various applications (e.g., autonomous driving, and anomaly detection). Most of the existing methods focus on homogeneous pedestrian trajectories prediction, where pedestrians are treated as particles without size. However, they fall short of handling crowded vehicle-pedestrian-mixed scenes directly since vehicles, limited with kinematics in reality, should be treated as rigid, non-particle objects ideally. In this paper, we tackle this problem using separate LSTMs for heterogeneous vehicles and pedestrians. Specifically, we use an oriented bounding box to represent each vehicle, calculated based on its position and orientation, to denote its kinematic trajectories. We then propose a framework called VP-LSTM to predict the kinematic trajectories of both vehicles and pedestrians simultaneously. In order to evaluate our model, a large dataset containing the trajectories of both vehicles and pedestrians in vehicle-pedestrian-mixed scenes is specially built. Through comparisons between our method with state-of-the-art approaches, we show the effectiveness and advantages of our method on kinematic trajectories prediction in vehicle-pedestrian-mixed scenes.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"51 1","pages":"10382-10391"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82267191","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}
Erickson R. Nascimento, Guilherme A. Potje, Renato Martins, Felipe C. Chamone, M. Campos, R. Bajcsy
At the core of most three-dimensional alignment and tracking tasks resides the critical problem of point correspondence. In this context, the design of descriptors that efficiently and uniquely identifies keypoints, to be matched, is of central importance. Numerous descriptors have been developed for dealing with affine/perspective warps, but few can also handle non-rigid deformations. In this paper, we introduce a novel binary RGB-D descriptor invariant to isometric deformations. Our method uses geodesic isocurves on smooth textured manifolds. It combines appearance and geometric information from RGB-D images to tackle non-rigid transformations. We used our descriptor to track multiple textured depth maps and demonstrate that it produces reliable feature descriptors even in the presence of strong non-rigid deformations and depth noise. The experiments show that our descriptor outperforms different state-of-the-art descriptors in both precision-recall and recognition rate metrics. We also provide to the community a new dataset composed of annotated RGB-D images of different objects (shirts, cloths, paintings, bags), subjected to strong non-rigid deformations, to evaluate point correspondence algorithms.
{"title":"GEOBIT: A Geodesic-Based Binary Descriptor Invariant to Non-Rigid Deformations for RGB-D Images","authors":"Erickson R. Nascimento, Guilherme A. Potje, Renato Martins, Felipe C. Chamone, M. Campos, R. Bajcsy","doi":"10.1109/ICCV.2019.01010","DOIUrl":"https://doi.org/10.1109/ICCV.2019.01010","url":null,"abstract":"At the core of most three-dimensional alignment and tracking tasks resides the critical problem of point correspondence. In this context, the design of descriptors that efficiently and uniquely identifies keypoints, to be matched, is of central importance. Numerous descriptors have been developed for dealing with affine/perspective warps, but few can also handle non-rigid deformations. In this paper, we introduce a novel binary RGB-D descriptor invariant to isometric deformations. Our method uses geodesic isocurves on smooth textured manifolds. It combines appearance and geometric information from RGB-D images to tackle non-rigid transformations. We used our descriptor to track multiple textured depth maps and demonstrate that it produces reliable feature descriptors even in the presence of strong non-rigid deformations and depth noise. The experiments show that our descriptor outperforms different state-of-the-art descriptors in both precision-recall and recognition rate metrics. We also provide to the community a new dataset composed of annotated RGB-D images of different objects (shirts, cloths, paintings, bags), subjected to strong non-rigid deformations, to evaluate point correspondence algorithms.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"85 1","pages":"10003-10011"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76050172","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}
Joseph R. Bartels, Jian Wang, W. Whittaker, S. Narasimhan
Depth sensors like LIDARs and Kinect use a fixed depth acquisition strategy that is independent of the scene of interest. Due to the low spatial and temporal resolution of these sensors, this strategy can undersample parts of the scene that are important (small or fast moving objects), or oversample areas that are not informative for the task at hand (a fixed planar wall). In this paper, we present an approach and system to dynamically and adaptively sample the depths of a scene using the principle of triangulation light curtains. The approach directly detects the presence or absence of objects at specified 3D lines. These 3D lines can be sampled sparsely, non-uniformly, or densely only at specified regions. The depth sampling can be varied in real-time, enabling quick object discovery or detailed exploration of areas of interest. These results are achieved using a novel prototype light curtain system that is based on a 2D rolling shutter camera with higher light efficiency, working range, and faster adaptation than previous work, making it useful broadly for autonomous navigation and exploration.
{"title":"Agile Depth Sensing Using Triangulation Light Curtains","authors":"Joseph R. Bartels, Jian Wang, W. Whittaker, S. Narasimhan","doi":"10.1109/ICCV.2019.00799","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00799","url":null,"abstract":"Depth sensors like LIDARs and Kinect use a fixed depth acquisition strategy that is independent of the scene of interest. Due to the low spatial and temporal resolution of these sensors, this strategy can undersample parts of the scene that are important (small or fast moving objects), or oversample areas that are not informative for the task at hand (a fixed planar wall). In this paper, we present an approach and system to dynamically and adaptively sample the depths of a scene using the principle of triangulation light curtains. The approach directly detects the presence or absence of objects at specified 3D lines. These 3D lines can be sampled sparsely, non-uniformly, or densely only at specified regions. The depth sampling can be varied in real-time, enabling quick object discovery or detailed exploration of areas of interest. These results are achieved using a novel prototype light curtain system that is based on a 2D rolling shutter camera with higher light efficiency, working range, and faster adaptation than previous work, making it useful broadly for autonomous navigation and exploration.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"8 1","pages":"7899-7907"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87530700","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}
Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aware models design unidirectional frameworks which only use edge features to improve the segmentation features. Motivated by the logical interrelations between binary segmentation and edge maps, we propose a novel Stacked Cross Refinement Network (SCRN) for salient object detection in this paper. Our framework aims to simultaneously refine multi-level features of salient object detection and edge detection by stacking Cross Refinement Unit (CRU). According to the logical interrelations, the CRU designs two direction-specific integration operations, and bidirectionally passes messages between the two tasks. Incorporating the refined edge-preserving features with the typical U-Net, our model detects salient objects accurately. Extensive experiments conducted on six benchmark datasets demonstrate that our method outperforms existing state-of-the-art algorithms in both accuracy and efficiency. Besides, the attribute-based performance on the SOC dataset show that the proposed model ranks first in the majority of challenging scenes. Code can be found at https://github.com/wuzhe71/SCAN.
显著目标检测是一项基本的计算机视觉任务。现有的卷积神经网络算法主要集中在对预训练卷积神经网络的多层特征进行聚合。此外，一些研究者试图利用边缘信息进行辅助训练。然而，现有的边缘感知模型设计了单向框架，仅利用边缘特征来改进分割特征。基于二值分割与边缘映射之间的逻辑关系，提出了一种新的用于显著目标检测的堆叠交叉细化网络(SCRN)。我们的框架旨在通过叠加交叉细化单元(Cross Refinement Unit, CRU)来同时细化显著目标检测和边缘检测的多层次特征。CRU根据逻辑关系设计两个特定方向的集成操作，并在两个任务之间双向传递消息。该模型将改进的边缘保持特征与典型的U-Net相结合，能够准确地检测出显著目标。在六个基准数据集上进行的大量实验表明，我们的方法在准确性和效率方面都优于现有的最先进算法。此外，基于属性的SOC数据集性能表明，该模型在大多数具有挑战性的场景中排名第一。代码可以在https://github.com/wuzhe71/SCAN上找到。
{"title":"Stacked Cross Refinement Network for Edge-Aware Salient Object Detection","authors":"Zhe Wu, Li Su, Qingming Huang","doi":"10.1109/ICCV.2019.00736","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00736","url":null,"abstract":"Salient object detection is a fundamental computer vision task. The majority of existing algorithms focus on aggregating multi-level features of pre-trained convolutional neural networks. Moreover, some researchers attempt to utilize edge information for auxiliary training. However, existing edge-aware models design unidirectional frameworks which only use edge features to improve the segmentation features. Motivated by the logical interrelations between binary segmentation and edge maps, we propose a novel Stacked Cross Refinement Network (SCRN) for salient object detection in this paper. Our framework aims to simultaneously refine multi-level features of salient object detection and edge detection by stacking Cross Refinement Unit (CRU). According to the logical interrelations, the CRU designs two direction-specific integration operations, and bidirectionally passes messages between the two tasks. Incorporating the refined edge-preserving features with the typical U-Net, our model detects salient objects accurately. Extensive experiments conducted on six benchmark datasets demonstrate that our method outperforms existing state-of-the-art algorithms in both accuracy and efficiency. Besides, the attribute-based performance on the SOC dataset show that the proposed model ranks first in the majority of challenging scenes. Code can be found at https://github.com/wuzhe71/SCAN.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"9 1","pages":"7263-7272"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88062889","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}
Recent advances in Generative Adversarial Networks (GANs) have made it possible to conduct multi-domain image-to-image translation using a single generative network. While recent methods such as Ganimation and SaGAN are able to conduct translations on attribute-relevant regions using attention, they do not perform well when the number of attributes increases as the training of attention masks mostly rely on classification losses. To address this and other limitations, we introduce Attribute Manipulation Generative Adversarial Networks (AMGAN) for fashion images. While AMGAN's generator network uses class activation maps (CAMs) to empower its attention mechanism, it also exploits perceptual losses by assigning reference (target) images based on attribute similarities. AMGAN incorporates an additional discriminator network that focuses on attribute-relevant regions to detect unrealistic translations. Additionally, AMGAN can be controlled to perform attribute manipulations on specific regions such as the sleeve or torso regions. Experiments show that AMGAN outperforms state-of-the-art methods using traditional evaluation metrics as well as an alternative one that is based on image retrieval.
{"title":"Attribute Manipulation Generative Adversarial Networks for Fashion Images","authors":"Kenan E. Ak, A. Kassim, Joo-Hwee Lim, J. Y. Tham","doi":"10.1109/ICCV.2019.01064","DOIUrl":"https://doi.org/10.1109/ICCV.2019.01064","url":null,"abstract":"Recent advances in Generative Adversarial Networks (GANs) have made it possible to conduct multi-domain image-to-image translation using a single generative network. While recent methods such as Ganimation and SaGAN are able to conduct translations on attribute-relevant regions using attention, they do not perform well when the number of attributes increases as the training of attention masks mostly rely on classification losses. To address this and other limitations, we introduce Attribute Manipulation Generative Adversarial Networks (AMGAN) for fashion images. While AMGAN's generator network uses class activation maps (CAMs) to empower its attention mechanism, it also exploits perceptual losses by assigning reference (target) images based on attribute similarities. AMGAN incorporates an additional discriminator network that focuses on attribute-relevant regions to detect unrealistic translations. Additionally, AMGAN can be controlled to perform attribute manipulations on specific regions such as the sleeve or torso regions. Experiments show that AMGAN outperforms state-of-the-art methods using traditional evaluation metrics as well as an alternative one that is based on image retrieval.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"24 1","pages":"10540-10549"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86518855","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}
In this paper, we tackle the problem of depth completion from RGBD data. Towards this goal, we design a simple yet effective neural network block that learns to extract joint 2D and 3D features. Specifically, the block consists of two domain-specific sub-networks that apply 2D convolution on image pixels and continuous convolution on 3D points, with their output features fused in image space. We build the depth completion network simply by stacking the proposed block, which has the advantage of learning hierarchical representations that are fully fused between 2D and 3D spaces at multiple levels. We demonstrate the effectiveness of our approach on the challenging KITTI depth completion benchmark and show that our approach outperforms the state-of-the-art.
{"title":"Learning Joint 2D-3D Representations for Depth Completion","authors":"Yuxiang Chen, Binh Yang, Ming Liang, R. Urtasun","doi":"10.1109/ICCV.2019.01012","DOIUrl":"https://doi.org/10.1109/ICCV.2019.01012","url":null,"abstract":"In this paper, we tackle the problem of depth completion from RGBD data. Towards this goal, we design a simple yet effective neural network block that learns to extract joint 2D and 3D features. Specifically, the block consists of two domain-specific sub-networks that apply 2D convolution on image pixels and continuous convolution on 3D points, with their output features fused in image space. We build the depth completion network simply by stacking the proposed block, which has the advantage of learning hierarchical representations that are fully fused between 2D and 3D spaces at multiple levels. We demonstrate the effectiveness of our approach on the challenging KITTI depth completion benchmark and show that our approach outperforms the state-of-the-art.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"21 1","pages":"10022-10031"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83955185","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}
Adversarial representation learning is a promising paradigm for obtaining data representations that are invariant to certain sensitive attributes while retaining the information necessary for predicting target attributes. Existing approaches solve this problem through iterative adversarial minimax optimization and lack theoretical guarantees. In this paper, we first study the ``linear" form of this problem i.e., the setting where all the players are linear functions. We show that the resulting optimization problem is both non-convex and non-differentiable. We obtain an exact closed-form expression for its global optima through spectral learning and provide performance guarantees in terms of analytical bounds on the achievable utility and invariance. We then extend this solution and analysis to non-linear functions through kernel representation. Numerical experiments on UCI, Extended Yale B and CIFAR-100 datasets indicate that, (a) practically, our solution is ideal for ``imparting" provable invariance to any biased pre-trained data representation, and (b) the global optima of the ``kernel" form can provide a comparable trade-off between utility and invariance in comparison to iterative minimax optimization of existing deep neural network based approaches, but with provable guarantees.
{"title":"On the Global Optima of Kernelized Adversarial Representation Learning","authors":"Bashir Sadeghi, R. Yu, Vishnu Naresh Boddeti","doi":"10.1109/ICCV.2019.00806","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00806","url":null,"abstract":"Adversarial representation learning is a promising paradigm for obtaining data representations that are invariant to certain sensitive attributes while retaining the information necessary for predicting target attributes. Existing approaches solve this problem through iterative adversarial minimax optimization and lack theoretical guarantees. In this paper, we first study the ``linear\" form of this problem i.e., the setting where all the players are linear functions. We show that the resulting optimization problem is both non-convex and non-differentiable. We obtain an exact closed-form expression for its global optima through spectral learning and provide performance guarantees in terms of analytical bounds on the achievable utility and invariance. We then extend this solution and analysis to non-linear functions through kernel representation. Numerical experiments on UCI, Extended Yale B and CIFAR-100 datasets indicate that, (a) practically, our solution is ideal for ``imparting\" provable invariance to any biased pre-trained data representation, and (b) the global optima of the ``kernel\" form can provide a comparable trade-off between utility and invariance in comparison to iterative minimax optimization of existing deep neural network based approaches, but with provable guarantees.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"22 8 1","pages":"7970-7978"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82923046","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}
Yudong Chen, Zhihui Lai, Yujuan Ding, Kaiyi Lin, W. Wong
Recently, a series of deep supervised hashing methods were proposed for binary code learning. However, due to the high computation cost and the limited hardware's memory, these methods will first select a subset from the training set, and then form a mini-batch data to update the network in each iteration. Therefore, the remaining labeled data cannot be fully utilized and the model cannot directly obtain the binary codes of the entire training set for retrieval. To address these problems, this paper proposes an interesting regularized deep model to seamlessly integrate the advantages of deep hashing and efficient binary code learning by using the anchor graph. As such, the deep features and label matrix can be jointly used to optimize the binary codes, and the network can obtain more discriminative feedback from the linear combinations of the learned bits. Moreover, we also reveal the algorithm mechanism and its computation essence. Experiments on three large-scale datasets indicate that the proposed method achieves better retrieval performance with less training time compared to previous deep hashing methods.
{"title":"Deep Supervised Hashing With Anchor Graph","authors":"Yudong Chen, Zhihui Lai, Yujuan Ding, Kaiyi Lin, W. Wong","doi":"10.1109/ICCV.2019.00989","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00989","url":null,"abstract":"Recently, a series of deep supervised hashing methods were proposed for binary code learning. However, due to the high computation cost and the limited hardware's memory, these methods will first select a subset from the training set, and then form a mini-batch data to update the network in each iteration. Therefore, the remaining labeled data cannot be fully utilized and the model cannot directly obtain the binary codes of the entire training set for retrieval. To address these problems, this paper proposes an interesting regularized deep model to seamlessly integrate the advantages of deep hashing and efficient binary code learning by using the anchor graph. As such, the deep features and label matrix can be jointly used to optimize the binary codes, and the network can obtain more discriminative feedback from the linear combinations of the learned bits. Moreover, we also reveal the algorithm mechanism and its computation essence. Experiments on three large-scale datasets indicate that the proposed method achieves better retrieval performance with less training time compared to previous deep hashing methods.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"89 1","pages":"9795-9803"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88997215","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：