2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)最新文献_第4页

Weakly Supervised Image Classification Through Noise Regularization 基于噪声正则化的弱监督图像分类

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.01178

Mengying Hu, Hu Han, S. Shan, Xilin Chen

{"title":"Weakly Supervised Image Classification Through Noise Regularization","authors":"Mengying Hu, Hu Han, S. Shan, Xilin Chen","doi":"10.1109/CVPR.2019.01178","DOIUrl":"https://doi.org/10.1109/CVPR.2019.01178","url":null,"abstract":"Weakly supervised learning is an essential problem in computer vision tasks, such as image classification, object recognition, etc., because it is expected to work in the scenarios where a large dataset with clean labels is not available. While there are a number of studies on weakly supervised image classification, they usually limited to either single-label or multi-label scenarios. In this work, we propose an effective approach for weakly supervised image classification utilizing massive noisy labeled data with only a small set of clean labels (e.g., 5%). The proposed approach consists of a clean net and a residual net, which aim to learn a mapping from feature space to clean label space and a residual mapping from feature space to the residual between clean labels and noisy labels, respectively, in a multi-task learning manner. Thus, the residual net works as a regularization term to improve the clean net training. We evaluate the proposed approach on two multi-label datasets (OpenImage and MS COCO2014) and a single-label dataset (Clothing1M). Experimental results show that the proposed approach outperforms the state-of-the-art methods, and generalizes well to both single-label and multi-label scenarios.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"59 1","pages":"11509-11517"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88388244","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 28

Towards Natural and Accurate Future Motion Prediction of Humans and Animals 人类和动物未来运动的自然准确预测

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.01024

Zhenguang Liu, Shuang Wu, Shuyuan Jin, Qi Liu, Shijian Lu, Roger Zimmermann, Li Cheng

{"title":"Towards Natural and Accurate Future Motion Prediction of Humans and Animals","authors":"Zhenguang Liu, Shuang Wu, Shuyuan Jin, Qi Liu, Shijian Lu, Roger Zimmermann, Li Cheng","doi":"10.1109/CVPR.2019.01024","DOIUrl":"https://doi.org/10.1109/CVPR.2019.01024","url":null,"abstract":"Anticipating the future motions of 3D articulate objects is challenging due to its non-linear and highly stochastic nature. Current approaches typically represent the skeleton of an articulate object as a set of 3D joints, which unfortunately ignores the relationship between joints, and fails to encode fine-grained anatomical constraints. Moreover, conventional recurrent neural networks, such as LSTM and GRU, are employed to model motion contexts, which inherently have difficulties in capturing long-term dependencies. To address these problems, we propose to explicitly encode anatomical constraints by modeling their skeletons with a Lie algebra representation. Importantly, a hierarchical recurrent network structure is developed to simultaneously encodes local contexts of individual frames and global contexts of the sequence. We proceed to explore the applications of our approach to several distinct quantities including human, fish, and mouse. Extensive experiments show that our approach achieves more natural and accurate predictions over state-of-the-art methods.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"50 1","pages":"9996-10004"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82946798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 89

DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features DeFusionNET:通过循环融合和细化多尺度深度特征的散焦模糊检测

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00281

Chang Tang, Xinzhong Zhu, Xinwang Liu, Lizhe Wang, Albert Y. Zomaya

{"title":"DeFusionNET: Defocus Blur Detection via Recurrently Fusing and Refining Multi-Scale Deep Features","authors":"Chang Tang, Xinzhong Zhu, Xinwang Liu, Lizhe Wang, Albert Y. Zomaya","doi":"10.1109/CVPR.2019.00281","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00281","url":null,"abstract":"Defocus blur detection aims to detect out-of-focus regions from an image. Although attracting more and more attention due to its widespread applications, defocus blur detection still confronts several challenges such as the interference of background clutter, sensitivity to scales and missing boundary details of defocus blur regions. To deal with these issues, we propose a deep neural network which recurrently fuses and refines multi-scale deep features (DeFusionNet) for defocus blur detection. We firstly utilize a fully convolutional network to extract multi-scale deep features. The features from bottom layers are able to capture rich low-level features for details preservation, while the features from top layers can characterize the semantic information to locate blur regions. These features from different layers are fused as shallow features and semantic features, respectively. After that, the fused shallow features are propagated to top layers for refining the fine details of detected defocus blur regions, and the fused semantic features are propagated to bottom layers to assist in better locating the defocus regions. The feature fusing and refining are carried out in a recurrent manner. Also, we finally fuse the output of each layer at the last recurrent step to obtain the final defocus blur map by considering the sensitivity to scales of the defocus degree. Experiments on two commonly used defocus blur detection benchmark datasets are conducted to demonstrate the superority of DeFusionNet when compared with other 10 competitors. Code and more results can be found at: http://tangchang.net","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"50 1","pages":"2695-2704"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90047273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 55

A Local Block Coordinate Descent Algorithm for the CSC Model 一种CSC模型的局部块坐标下降算法

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00840

E. Zisselman, Jeremias Sulam, Michael Elad

{"title":"A Local Block Coordinate Descent Algorithm for the CSC Model","authors":"E. Zisselman, Jeremias Sulam, Michael Elad","doi":"10.1109/CVPR.2019.00840","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00840","url":null,"abstract":"The Convolutional Sparse Coding (CSC) model has recently gained considerable traction in the signal and image processing communities. By providing a global, yet tractable, model that operates on the whole image, the CSC was shown to overcome several limitations of the patch-based sparse model while achieving superior performance in various applications. Contemporary methods for pursuit and learning the CSC dictionary often rely on the Alternating Direction Method of Multipliers (ADMM) in the Fourier domain for the computational convenience of convolutions, while ignoring the local characterizations of the image. In this work we propose a new and simple approach that adopts a localized strategy, based on the Block Coordinate Descent algorithm. The proposed method, termed Local Block Coordinate Descent (LoBCoD), operates locally on image patches. Furthermore, we introduce a novel stochastic gradient descent version of LoBCoD for training the convolutional filters. This Stochastic-LoBCoD leverages the benefits of online learning, while being applicable even to a single training image. We demonstrate the advantages of the proposed algorithms for image inpainting and multi-focus image fusion, achieving state-of-the-art results.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"28 1","pages":"8200-8209"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90481659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 31

Iterative Alignment Network for Continuous Sign Language Recognition 连续手语识别的迭代对齐网络

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00429

Junfu Pu, Wen-gang Zhou, Houqiang Li

{"title":"Iterative Alignment Network for Continuous Sign Language Recognition","authors":"Junfu Pu, Wen-gang Zhou, Houqiang Li","doi":"10.1109/CVPR.2019.00429","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00429","url":null,"abstract":"In this paper, we propose an alignment network with iterative optimization for weakly supervised continuous sign language recognition. Our framework consists of two modules: a 3D convolutional residual network (3D-ResNet) for feature learning and an encoder-decoder network with connectionist temporal classification (CTC) for sequence modelling. The above two modules are optimized in an alternate way. In the encoder-decoder sequence learning network, two decoders are included, i.e., LSTM decoder and CTC decoder. Both decoders are jointly trained by maximum likelihood criterion with a soft Dynamic Time Warping (soft-DTW) alignment constraint. The warping path, which indicates the possible alignment between input video clips and sign words, is used to fine-tune the 3D-ResNet as training labels with classification loss. After fine-tuning, the improved features are extracted for optimization of encoder-decoder sequence learning network in next iteration. The proposed algorithm is evaluated on two large scale continuous sign language recognition benchmarks, i.e., RWTH-PHOENIX-Weather and CSL. Experimental results demonstrate the effectiveness of our proposed method.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"684 1","pages":"4160-4169"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91445019","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 140

Learning Multi-Class Segmentations From Single-Class Datasets 从单类数据集学习多类分割

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00973

Konstantin Dmitriev, A. Kaufman

{"title":"Learning Multi-Class Segmentations From Single-Class Datasets","authors":"Konstantin Dmitriev, A. Kaufman","doi":"10.1109/CVPR.2019.00973","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00973","url":null,"abstract":"Multi-class segmentation has recently achieved significant performance in natural images and videos. This achievement is due primarily to the public availability of large multi-class datasets. However, there are certain domains, such as biomedical images, where obtaining sufficient multi-class annotations is a laborious and often impossible task and only single-class datasets are available. While existing segmentation research in such domains use private multi-class datasets or focus on single-class segmentations, we propose a unified highly efficient framework for robust simultaneous learning of multi-class segmentations by combining single-class datasets and utilizing a novel way of conditioning a convolutional network for the purpose of segmentation. We demonstrate various ways of incorporating the conditional information, perform an extensive evaluation, and show compelling multi-class segmentation performance on biomedical images, which outperforms current state-of-the-art solutions (up to 2.7%). Unlike current solutions, which are meticulously tailored for particular single-class datasets, we utilize datasets from a variety of sources. Furthermore, we show the applicability of our method also to natural images and evaluate it on the Cityscapes dataset. We further discuss other possible applications of our proposed framework.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"253 1","pages":"9493-9503"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79686703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 38

How to Make a Pizza: Learning a Compositional Layer-Based GAN Model 如何制作披萨:学习基于合成层的GAN模型

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00819

Dim P. Papadopoulos, Y. Tamaazousti, Ferda Ofli, Ingmar Weber, A. Torralba

{"title":"How to Make a Pizza: Learning a Compositional Layer-Based GAN Model","authors":"Dim P. Papadopoulos, Y. Tamaazousti, Ferda Ofli, Ingmar Weber, A. Torralba","doi":"10.1109/CVPR.2019.00819","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00819","url":null,"abstract":"A food recipe is an ordered set of instructions for preparing a particular dish. From a visual perspective, every instruction step can be seen as a way to change the visual appearance of the dish by adding extra objects (e.g., adding an ingredient) or changing the appearance of the existing ones (e.g., cooking the dish). In this paper, we aim to teach a machine how to make a pizza by building a generative model that mirrors this step-by-step procedure. To do so, we learn composable module operations which are able to either add or remove a particular ingredient. Each operator is designed as a Generative Adversarial Network (GAN). Given only weak image-level supervision, the operators are trained to generate a visual layer that needs to be added to or removed from the existing image. The proposed model is able to decompose an image into an ordered sequence of layers by applying sequentially in the right order the corresponding removing modules. Experimental results on synthetic and real pizza images demonstrate that our proposed model is able to: (1) segment pizza toppings in a weakly- supervised fashion, (2) remove them by revealing what is occluded underneath them (i.e., inpainting), and (3) infer the ordering of the toppings without any depth ordering supervision. Code, data, and models are available online.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"25 1","pages":"7994-8003"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83418886","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 32

Grounding Human-To-Vehicle Advice for Self-Driving Vehicles 为自动驾驶汽车提供接地人对车建议

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.01084

Jinkyu Kim, Teruhisa Misu, Yi-Ting Chen, Ashish Tawari, J. Canny

{"title":"Grounding Human-To-Vehicle Advice for Self-Driving Vehicles","authors":"Jinkyu Kim, Teruhisa Misu, Yi-Ting Chen, Ashish Tawari, J. Canny","doi":"10.1109/CVPR.2019.01084","DOIUrl":"https://doi.org/10.1109/CVPR.2019.01084","url":null,"abstract":"Recent success suggests that deep neural control networks are likely to be a key component of self-driving vehicles. These networks are trained on large datasets to imitate human actions, but they lack semantic understanding of image contents. This makes them brittle and potentially unsafe in situations that do not match training data. Here, we propose to address this issue by augmenting training data with natural language advice from a human. Advice includes guidance about what to do and where to attend. We present the first step toward advice giving, where we train an end-to-end vehicle controller that accepts advice. The controller adapts the way it attends to the scene (visual attention) and the control (steering and speed). Attention mechanisms tie controller behavior to salient objects in the advice. We evaluate our model on a novel advisable driving dataset with manually annotated human-to-vehicle advice called Honda Research Institute-Advice Dataset (HAD). We show that taking advice improves the performance of the end-to-end network, while the network cues on a variety of visual features that are provided by advice. The dataset is available at https://usa.honda-ri.com/HAD.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"72 1","pages":"10583-10591"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87370643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 51

Compressing Convolutional Neural Networks via Factorized Convolutional Filters 基于分解卷积滤波器的卷积神经网络压缩

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00410

T. Li, Baoyuan Wu, Yujiu Yang, Yanbo Fan, Yong Zhang, Wei Liu

{"title":"Compressing Convolutional Neural Networks via Factorized Convolutional Filters","authors":"T. Li, Baoyuan Wu, Yujiu Yang, Yanbo Fan, Yong Zhang, Wei Liu","doi":"10.1109/CVPR.2019.00410","DOIUrl":"https://doi.org/10.1109/CVPR.2019.00410","url":null,"abstract":"This work studies the model compression for deep convolutional neural networks (CNNs) via filter pruning. The workflow of a traditional pruning consists of three sequential stages: pre-training the original model, selecting the pre-trained filters via ranking according to a manually designed criterion (e.g., the norm of filters), and learning the remained filters via fine-tuning. Most existing works follow this pipeline and focus on designing different ranking criteria for filter selection. However, it is difficult to control the performance due to the separation of filter selection and filter learning. In this work, we propose to conduct filter selection and filter learning simultaneously, in a unified model. To this end, we define a factorized convolutional filter (FCF), consisting of a standard real-valued convolutional filter and a binary scalar, as well as a dot-product operator between them. We train a CNN model with factorized convolutional filters (CNN-FCF) by updating the standard filter using back-propagation, while updating the binary scalar using the alternating direction method of multipliers (ADMM) based optimization method. With this trained CNN-FCF model, we only keep the standard filters corresponding to the 1-valued scalars, while all other filters and all binary scalars are discarded, to obtain a compact CNN model. Extensive experiments on CIFAR-10 and ImageNet demonstrate the superiority of the proposed method over state-of-the-art filter pruning methods.","PeriodicalId":6711,"journal":{"name":"2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","volume":"119 1","pages":"3972-3981"},"PeriodicalIF":0.0,"publicationDate":"2019-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80610048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 86

Large-Scale Few-Shot Learning: Knowledge Transfer With Class Hierarchy 大规模的少镜头学习:类层次的知识转移

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Pub Date : 2019-06-01 DOI: 10.1109/CVPR.2019.00738

Aoxue Li, Tiange Luo, Zhiwu Lu, T. Xiang, Liwei Wang

引用次数: 105