Siamese networks are non-linear deep models that have found their ways into a broad set of problems in learning theory, thanks to their embedding capabilities. In this paper, we study Siamese networks from a new perspective and question the validity of their training procedure. We show that in the majority of cases, the objective of a Siamese network is endowed with an invariance property. Neglecting the invariance property leads to a hindrance in training the Siamese networks. To alleviate this issue, we propose two Riemannian structures and generalize a well-established accelerated stochastic gradient descent method to take into account the proposed Riemannian structures. Our empirical evaluations suggest that by making use of the Riemannian geometry, we achieve state-of-the-art results against several algorithms for the challenging problem of fine-grained image classification.
{"title":"Siamese Networks: The Tale of Two Manifolds","authors":"S. Roy, M. Harandi, R. Nock, R. Hartley","doi":"10.1109/ICCV.2019.00314","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00314","url":null,"abstract":"Siamese networks are non-linear deep models that have found their ways into a broad set of problems in learning theory, thanks to their embedding capabilities. In this paper, we study Siamese networks from a new perspective and question the validity of their training procedure. We show that in the majority of cases, the objective of a Siamese network is endowed with an invariance property. Neglecting the invariance property leads to a hindrance in training the Siamese networks. To alleviate this issue, we propose two Riemannian structures and generalize a well-established accelerated stochastic gradient descent method to take into account the proposed Riemannian structures. Our empirical evaluations suggest that by making use of the Riemannian geometry, we achieve state-of-the-art results against several algorithms for the challenging problem of fine-grained image classification.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"25 1","pages":"3046-3055"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89067744","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}
M. Kashiwagi, Nao Mishima, Tatsuo Kozakaya, S. Hiura
Passive and convenient depth estimation from single-shot image is still an open problem. Existing depth from defocus methods require multiple input images or special hardware customization. Recent deep monocular depth estimation is also limited to an image with sufficient contextual information. In this work, we propose a novel method which realizes a single-shot deep depth measurement based on physical depth cue using only an off-the-shelf camera and lens. When a defocused image is taken by a camera, it contains various types of aberrations corresponding to distances from the image sensor and positions in the image plane. We call these minute and complexly compound aberrations as Aberration Map (A-Map) and we found that A-Map can be utilized as reliable physical depth cue. Additionally, our deep network named A-Map Analysis Network (AMA-Net) is also proposed, which can effectively learn and estimate depth via A-Map. To evaluate validity and robustness of our approach, we have conducted extensive experiments using both real outdoor scenes and simulated images. The qualitative result shows the accuracy and availability of the method in comparison with a state-of-the-art deep context-based method.
{"title":"Deep Depth From Aberration Map","authors":"M. Kashiwagi, Nao Mishima, Tatsuo Kozakaya, S. Hiura","doi":"10.1109/ICCV.2019.00417","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00417","url":null,"abstract":"Passive and convenient depth estimation from single-shot image is still an open problem. Existing depth from defocus methods require multiple input images or special hardware customization. Recent deep monocular depth estimation is also limited to an image with sufficient contextual information. In this work, we propose a novel method which realizes a single-shot deep depth measurement based on physical depth cue using only an off-the-shelf camera and lens. When a defocused image is taken by a camera, it contains various types of aberrations corresponding to distances from the image sensor and positions in the image plane. We call these minute and complexly compound aberrations as Aberration Map (A-Map) and we found that A-Map can be utilized as reliable physical depth cue. Additionally, our deep network named A-Map Analysis Network (AMA-Net) is also proposed, which can effectively learn and estimate depth via A-Map. To evaluate validity and robustness of our approach, we have conducted extensive experiments using both real outdoor scenes and simulated images. The qualitative result shows the accuracy and availability of the method in comparison with a state-of-the-art deep context-based method.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"81 1","pages":"4069-4078"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90491012","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}
Sai Bi, Kalyan Sunkavalli, Federico Perazzi, Eli Shechtman, Vladimir G. Kim, R. Ramamoorthi, U. Diego
We present a method to improve the visual realism of low-quality, synthetic images, e.g. OpenGL renderings. Training an unpaired synthetic-to-real translation network in image space is severely under-constrained and produces visible artifacts. Instead, we propose a semi-supervised approach that operates on the disentangled shading and albedo layers of the image. Our two-stage pipeline first learns to predict accurate shading in a supervised fashion using physically-based renderings as targets, and further increases the realism of the textures and shading with an improved CycleGAN network. Extensive evaluations on the SUNCG indoor scene dataset demonstrate that our approach yields more realistic images compared to other state-of-the-art approaches. Furthermore, networks trained on our generated ``real'' images predict more accurate depth and normals than domain adaptation approaches, suggesting that improving the visual realism of the images can be more effective than imposing task-specific losses.
{"title":"Deep CG2Real: Synthetic-to-Real Translation via Image Disentanglement","authors":"Sai Bi, Kalyan Sunkavalli, Federico Perazzi, Eli Shechtman, Vladimir G. Kim, R. Ramamoorthi, U. Diego","doi":"10.1109/ICCV.2019.00282","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00282","url":null,"abstract":"We present a method to improve the visual realism of low-quality, synthetic images, e.g. OpenGL renderings. Training an unpaired synthetic-to-real translation network in image space is severely under-constrained and produces visible artifacts. Instead, we propose a semi-supervised approach that operates on the disentangled shading and albedo layers of the image. Our two-stage pipeline first learns to predict accurate shading in a supervised fashion using physically-based renderings as targets, and further increases the realism of the textures and shading with an improved CycleGAN network. Extensive evaluations on the SUNCG indoor scene dataset demonstrate that our approach yields more realistic images compared to other state-of-the-art approaches. Furthermore, networks trained on our generated ``real'' images predict more accurate depth and normals than domain adaptation approaches, suggesting that improving the visual realism of the images can be more effective than imposing task-specific losses.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"120 1","pages":"2730-2739"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89138228","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, large-margin softmax loss methods, such as angular softmax loss (SphereFace), large margin cosine loss (CosFace), and additive angular margin loss (ArcFace), have demonstrated impressive performance on deep face recognition. These methods incorporate a fixed additive margin to all the classes, ignoring the class imbalance problem. However, imbalanced problem widely exists in various real-world face datasets, in which samples from some classes are in a higher number than others. We argue that the number of a class would influence its demand for the additive margin. In this paper, we introduce a new margin-aware reinforcement learning based loss function, namely fair loss, in which each class will learn an appropriate adaptive margin by Deep Q-learning. Specifically, we train an agent to learn a margin adaptive strategy for each class, and make the additive margins for different classes more reasonable. Our method has better performance than present large-margin loss functions on three benchmarks, Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace, which demonstrates that our method could learn better face representation on imbalanced face datasets.
近年来，角softmax损失(SphereFace)、大余弦损失(CosFace)和加性角余弦损失(ArcFace)等大余弦损失方法在深度人脸识别中表现出了令人印象深刻的性能。这些方法在所有类中加入了固定的附加裕度，忽略了类不平衡问题。然而，不平衡问题在现实世界的各种人脸数据集中广泛存在，其中某些类别的样本数量多于其他类别。我们认为，一个类别的数量将影响其对附加边际的需求。在本文中，我们引入了一种新的基于边缘感知强化学习的损失函数，即公平损失，其中每个类将通过深度q学习学习适当的自适应边缘。具体来说，我们训练智能体学习每个类别的边际自适应策略，使不同类别的附加边际更加合理。我们的方法在label Face in the Wild (LFW)、Youtube Faces (YTF)和MegaFace三个基准上的性能优于现有的大边际损失函数，这表明我们的方法可以在不平衡的人脸数据集上学习到更好的人脸表示。
{"title":"Fair Loss: Margin-Aware Reinforcement Learning for Deep Face Recognition","authors":"Bingyu Liu, Weihong Deng, Yaoyao Zhong, Mei Wang, Jiani Hu, Xunqiang Tao, Yaohai Huang","doi":"10.1109/ICCV.2019.01015","DOIUrl":"https://doi.org/10.1109/ICCV.2019.01015","url":null,"abstract":"Recently, large-margin softmax loss methods, such as angular softmax loss (SphereFace), large margin cosine loss (CosFace), and additive angular margin loss (ArcFace), have demonstrated impressive performance on deep face recognition. These methods incorporate a fixed additive margin to all the classes, ignoring the class imbalance problem. However, imbalanced problem widely exists in various real-world face datasets, in which samples from some classes are in a higher number than others. We argue that the number of a class would influence its demand for the additive margin. In this paper, we introduce a new margin-aware reinforcement learning based loss function, namely fair loss, in which each class will learn an appropriate adaptive margin by Deep Q-learning. Specifically, we train an agent to learn a margin adaptive strategy for each class, and make the additive margins for different classes more reasonable. Our method has better performance than present large-margin loss functions on three benchmarks, Labeled Face in the Wild (LFW), Youtube Faces (YTF) and MegaFace, which demonstrates that our method could learn better face representation on imbalanced face datasets.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"30 1","pages":"10051-10060"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80557702","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}
Marc-André Gardner, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Christian Gagné, Jean-François Lalonde
We present a method to estimate lighting from a single image of an indoor scene. Previous work has used an environment map representation that does not account for the localized nature of indoor lighting. Instead, we represent lighting as a set of discrete 3D lights with geometric and photometric parameters. We train a deep neural network to regress these parameters from a single image, on a dataset of environment maps annotated with depth. We propose a differentiable layer to convert these parameters to an environment map to compute our loss; this bypasses the challenge of establishing correspondences between estimated and ground truth lights. We demonstrate, via quantitative and qualitative evaluations, that our representation and training scheme lead to more accurate results compared to previous work, while allowing for more realistic 3D object compositing with spatially-varying lighting.
{"title":"Deep Parametric Indoor Lighting Estimation","authors":"Marc-André Gardner, Yannick Hold-Geoffroy, Kalyan Sunkavalli, Christian Gagné, Jean-François Lalonde","doi":"10.1109/ICCV.2019.00727","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00727","url":null,"abstract":"We present a method to estimate lighting from a single image of an indoor scene. Previous work has used an environment map representation that does not account for the localized nature of indoor lighting. Instead, we represent lighting as a set of discrete 3D lights with geometric and photometric parameters. We train a deep neural network to regress these parameters from a single image, on a dataset of environment maps annotated with depth. We propose a differentiable layer to convert these parameters to an environment map to compute our loss; this bypasses the challenge of establishing correspondences between estimated and ground truth lights. We demonstrate, via quantitative and qualitative evaluations, that our representation and training scheme lead to more accurate results compared to previous work, while allowing for more realistic 3D object compositing with spatially-varying lighting.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"10 1","pages":"7174-7182"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79699500","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}
Yongri Piao, Wei Ji, Jingjing Li, Miao Zhang, Huchuan Lu
In this work, we propose a novel depth-induced multi-scale recurrent attention network for saliency detection. It achieves dramatic performance especially in complex scenarios. There are three main contributions of our network that are experimentally demonstrated to have significant practical merits. First, we design an effective depth refinement block using residual connections to fully extract and fuse multi-level paired complementary cues from RGB and depth streams. Second, depth cues with abundant spatial information are innovatively combined with multi-scale context features for accurately locating salient objects. Third, we boost our model's performance by a novel recurrent attention module inspired by Internal Generative Mechanism of human brain. This module can generate more accurate saliency results via comprehensively learning the internal semantic relation of the fused feature and progressively optimizing local details with memory-oriented scene understanding. In addition, we create a large scale RGB-D dataset containing more complex scenarios, which can contribute to comprehensively evaluating saliency models. Extensive experiments on six public datasets and ours demonstrate that our method can accurately identify salient objects and achieve consistently superior performance over 16 state-of-the-art RGB and RGB-D approaches.
{"title":"Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection","authors":"Yongri Piao, Wei Ji, Jingjing Li, Miao Zhang, Huchuan Lu","doi":"10.1109/ICCV.2019.00735","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00735","url":null,"abstract":"In this work, we propose a novel depth-induced multi-scale recurrent attention network for saliency detection. It achieves dramatic performance especially in complex scenarios. There are three main contributions of our network that are experimentally demonstrated to have significant practical merits. First, we design an effective depth refinement block using residual connections to fully extract and fuse multi-level paired complementary cues from RGB and depth streams. Second, depth cues with abundant spatial information are innovatively combined with multi-scale context features for accurately locating salient objects. Third, we boost our model's performance by a novel recurrent attention module inspired by Internal Generative Mechanism of human brain. This module can generate more accurate saliency results via comprehensively learning the internal semantic relation of the fused feature and progressively optimizing local details with memory-oriented scene understanding. In addition, we create a large scale RGB-D dataset containing more complex scenarios, which can contribute to comprehensively evaluating saliency models. Extensive experiments on six public datasets and ours demonstrate that our method can accurately identify salient objects and achieve consistently superior performance over 16 state-of-the-art RGB and RGB-D approaches.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"31 1","pages":"7253-7262"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83191898","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}
Zimo Liu, Jingya Wang, S. Gong, D. Tao, Huchuan Lu
Most existing person re-identification(Re-ID) approaches achieve superior results based on the assumption that a large amount of pre-labelled data is usually available and can be put into training phrase all at once. However, this assumption is not applicable to most real-world deployment of the Re-ID task. In this work, we propose an alternative reinforcement learning based human-in-the-loop model which releases the restriction of pre-labelling and keeps model upgrading with progressively collected data. The goal is to minimize human annotation efforts while maximizing Re-ID performance. It works in an iteratively updating framework by refining the RL policy and CNN parameters alternately. In particular, we formulate a Deep Reinforcement Active Learning (DRAL) method to guide an agent (a model in a reinforcement learning process) in selecting training samples on-the-fly by a human user/annotator. The reinforcement learning reward is the uncertainty value of each human selected sample. A binary feedback (positive or negative) labelled by the human annotator is used to select the samples of which are used to fine-tune a pre-trained CNN Re-ID model. Extensive experiments demonstrate the superiority of our DRAL method for deep reinforcement learning based human-in-the-loop person Re-ID when compared to existing unsupervised and transfer learning models as well as active learning models.
{"title":"Deep Reinforcement Active Learning for Human-in-the-Loop Person Re-Identification","authors":"Zimo Liu, Jingya Wang, S. Gong, D. Tao, Huchuan Lu","doi":"10.1109/ICCV.2019.00622","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00622","url":null,"abstract":"Most existing person re-identification(Re-ID) approaches achieve superior results based on the assumption that a large amount of pre-labelled data is usually available and can be put into training phrase all at once. However, this assumption is not applicable to most real-world deployment of the Re-ID task. In this work, we propose an alternative reinforcement learning based human-in-the-loop model which releases the restriction of pre-labelling and keeps model upgrading with progressively collected data. The goal is to minimize human annotation efforts while maximizing Re-ID performance. It works in an iteratively updating framework by refining the RL policy and CNN parameters alternately. In particular, we formulate a Deep Reinforcement Active Learning (DRAL) method to guide an agent (a model in a reinforcement learning process) in selecting training samples on-the-fly by a human user/annotator. The reinforcement learning reward is the uncertainty value of each human selected sample. A binary feedback (positive or negative) labelled by the human annotator is used to select the samples of which are used to fine-tune a pre-trained CNN Re-ID model. Extensive experiments demonstrate the superiority of our DRAL method for deep reinforcement learning based human-in-the-loop person Re-ID when compared to existing unsupervised and transfer learning models as well as active learning models.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"15 1","pages":"6121-6130"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84641445","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}
Wei Feng, Wenhao He, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu
Most existing text spotting methods either focus on horizontal/oriented texts or perform arbitrary shaped text spotting with character-level annotations. In this paper, we propose a novel text spotting framework to detect and recognize text of arbitrary shapes in an end-to-end manner, using only word/line-level annotations for training. Motivated from the name of TextSnake, which is only a detection model, we call the proposed text spotting framework TextDragon. In TextDragon, a text detector is designed to describe the shape of text with a series of quadrangles, which can handle text of arbitrary shapes. To extract arbitrary text regions from feature maps, we propose a new differentiable operator named RoISlide, which is the key to connect arbitrary shaped text detection and recognition. Based on the extracted features through RoISlide, a CNN and CTC based text recognizer is introduced to make the framework free from labeling the location of characters. The proposed method achieves state-of-the-art performance on two curved text benchmarks CTW1500 and Total-Text, and competitive results on the ICDAR 2015 Dataset.
{"title":"TextDragon: An End-to-End Framework for Arbitrary Shaped Text Spotting","authors":"Wei Feng, Wenhao He, Fei Yin, Xu-Yao Zhang, Cheng-Lin Liu","doi":"10.1109/ICCV.2019.00917","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00917","url":null,"abstract":"Most existing text spotting methods either focus on horizontal/oriented texts or perform arbitrary shaped text spotting with character-level annotations. In this paper, we propose a novel text spotting framework to detect and recognize text of arbitrary shapes in an end-to-end manner, using only word/line-level annotations for training. Motivated from the name of TextSnake, which is only a detection model, we call the proposed text spotting framework TextDragon. In TextDragon, a text detector is designed to describe the shape of text with a series of quadrangles, which can handle text of arbitrary shapes. To extract arbitrary text regions from feature maps, we propose a new differentiable operator named RoISlide, which is the key to connect arbitrary shaped text detection and recognition. Based on the extracted features through RoISlide, a CNN and CTC based text recognizer is introduced to make the framework free from labeling the location of characters. The proposed method achieves state-of-the-art performance on two curved text benchmarks CTW1500 and Total-Text, and competitive results on the ICDAR 2015 Dataset.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"45 1","pages":"9075-9084"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87359527","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}
For matching pedestrians across disjoint camera views in surveillance, person re-identification (Re-ID) has made great progress in supervised learning. However, it is infeasible to label data in a number of new scenes when extending a Re-ID system. Thus, studying unsupervised learning for Re-ID is important for saving labelling cost. Yet, cross-camera scene variation is a key challenge for unsupervised Re-ID, such as illumination, background and viewpoint variations, which cause domain shift in the feature space and result in inconsistent pairwise similarity distributions that degrade matching performance. To alleviate the effect of cross-camera scene variation, we propose a Camera-Aware Similarity Consistency Loss to learn consistent pairwise similarity distributions for intra-camera matching and cross-camera matching. To avoid learning ineffective knowledge in consistency learning, we preserve the prior common knowledge of intra-camera matching in the pretrained model as reliable guiding information, which does not suffer from cross-camera scene variation as cross-camera matching. To learn similarity consistency more effectively, we further develop a coarse-to-fine consistency learning scheme to learn consistency globally and locally in two steps. Experiments show that our method outperformed the state-of-the-art unsupervised Re-ID methods.
{"title":"Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning","authors":"Ancong Wu, Weishi Zheng, J. Lai","doi":"10.1109/ICCV.2019.00702","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00702","url":null,"abstract":"For matching pedestrians across disjoint camera views in surveillance, person re-identification (Re-ID) has made great progress in supervised learning. However, it is infeasible to label data in a number of new scenes when extending a Re-ID system. Thus, studying unsupervised learning for Re-ID is important for saving labelling cost. Yet, cross-camera scene variation is a key challenge for unsupervised Re-ID, such as illumination, background and viewpoint variations, which cause domain shift in the feature space and result in inconsistent pairwise similarity distributions that degrade matching performance. To alleviate the effect of cross-camera scene variation, we propose a Camera-Aware Similarity Consistency Loss to learn consistent pairwise similarity distributions for intra-camera matching and cross-camera matching. To avoid learning ineffective knowledge in consistency learning, we preserve the prior common knowledge of intra-camera matching in the pretrained model as reliable guiding information, which does not suffer from cross-camera scene variation as cross-camera matching. To learn similarity consistency more effectively, we further develop a coarse-to-fine consistency learning scheme to learn consistency globally and locally in two steps. Experiments show that our method outperformed the state-of-the-art unsupervised Re-ID methods.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"9 1","pages":"6921-6930"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84712628","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}
Zhiqiang Tang, Xi Peng, Tingfeng Li, Yizhe Zhu, Dimitris N. Metaxas
Data augmentation is widely used to increase data variance in training deep neural networks. However, previous methods require either comprehensive domain knowledge or high computational cost. Can we learn data transformation automatically and efficiently with limited domain knowledge? Furthermore, can we leverage data transformation to improve not only network training but also network testing? In this work, we propose adaptive data transformation to achieve the two goals. The AdaTransform can increase data variance in training and decrease data variance in testing. Experiments on different tasks prove that it can improve generalization performance.
{"title":"AdaTransform: Adaptive Data Transformation","authors":"Zhiqiang Tang, Xi Peng, Tingfeng Li, Yizhe Zhu, Dimitris N. Metaxas","doi":"10.1109/ICCV.2019.00309","DOIUrl":"https://doi.org/10.1109/ICCV.2019.00309","url":null,"abstract":"Data augmentation is widely used to increase data variance in training deep neural networks. However, previous methods require either comprehensive domain knowledge or high computational cost. Can we learn data transformation automatically and efficiently with limited domain knowledge? Furthermore, can we leverage data transformation to improve not only network training but also network testing? In this work, we propose adaptive data transformation to achieve the two goals. The AdaTransform can increase data variance in training and decrease data variance in testing. Experiments on different tasks prove that it can improve generalization performance.","PeriodicalId":6728,"journal":{"name":"2019 IEEE/CVF International Conference on Computer Vision (ICCV)","volume":"171 1","pages":"2998-3006"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84794313","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：