|
|
|
题名
|
作者
|
年代
|
出处
|
被引量
|
| 1 | Uncertainty-optimized deep learning model for small-scale person re-identification显示文摘In recent years, deep learning has developed rapidly and is widely used in various fields, such as computer vision, speech recognition, and natural language processing. For end-to-end person re-identification,most deep learning methods rely on large-scale datasets. Relatively few methods work with small-scale datasets. Insufficient training samples will affect neural network accuracy significantly. This problem limits the practical application of person re-identification. For small-scale person re-identification, the uncertainty of person representation and the overfitting problem associated with deep learning remain to be solved.Quantifying the uncertainty is difficult owing to complex network structures and the large number of hyperparameters. In this study, we consider the uncertainty of pedestrian representation for small-scale person re-identification. To reduce the impact of uncertain person representations, we transform parameters into distributions and conduct multiple sampling by using multilevel dropout in a testing process. We design an improved Monte Carlo strategy that considers both the average distance and shortest distance for matching and ranking. When compared with state-of-the-art methods, the proposed method significantly improve accuracy on two small-scale person re-identification datasets and is robust on four large-scale datasets. | Cairong ZHAO Kang CHEN Di ZANG Zhaoxiang ZHANG Wangmeng ZUO Duoqian MIAO | 2019 | Science China(Information Sciences)2019，62，12： | 6 |
| 2 | An assembled matrix distance metric for 2DPCA-based image recognition显示文摘 | ZUO Wangmeng ZHANG D WANG Kuanquan | 2006 | Pattern Recognition Letters2006，27，3： | 1 |
| 3 | Combination of two novel LDA-based methods for face recognition 显示文摘 | ZUO Wangmeng WANG Kuanquan ZHANG David | 2007 | Advanced Neuro- computing Theory and Methodology2007，70，46： | 1 |
| 4 | An Assembled Matrix Distance Metric for 2DPCA-based Image Recognition 显示文摘 | Zuo Wangmeng Zhang D Wang Kuanquan | 2006 | Pattern Recognition Letters2006，27，3： | 1 |
| 5 | Gradient histogram estimation and preservation for texture enhanced image denoising显示文摘 | Zuo Wangmeng Zhang Lei Song Chunwei | 2014 | IEEE Trans on Image Processing2014，23，6： | 1 |
| 6 | Combination of two novel LDA-based methods for face recognition显示文摘 | ZUO Wangmeng WANG Kuanquan ZHANG David | | 0，，04： | 1 |
| 7 | Gradi- ent histogram estimation and preservation for texture en- hanced image denoising 显示文摘 | Zuo Wangmeng Zhang Lei Song Chunwei | 2014 | IEEE Transactions on Image Processing2014，23，6： | 1 |
| 8 | Combination of two novel LDA-based methods for face recognition显示文摘 | Zuo Wangmeng Wang Kuanquan Zhang D | 2007 | Neurocomputing2007，70，： | 1 |
| 9 | A u- nified distance measurement for orientation coding in palm- print verification显示文摘 | GUO Zhenhua ZUO Wangmeng ZHANG Lei | 2010 | Neurocomputing2010，73，456： | 1 |
| 10 | Combination of Polar Edge Detection and Ac-显示文摘 | Kuanquan Wang David Zhang Hong-zhi Zhang | 2004 | Image and Graphics2004，，： | 1 |
| 11 | Bidirectional PCA with assembled matrix distance metric for image recognition显示文摘 | Zuo Wangmeng ZHANG David | 2006 | IEEE Transaction on Machine Intelligence2006，36，4： | 1 |
| 12 | Supervised sparse rep- resentation method with a heuristic strategy and face recognition experiments 显示文摘 | Xu Yong Zuo Wangmeng Fan Zizhu | 2012 | Neurocomputing2012，79，1： | 1 |
| 13 | Fast gradient vector flow computation based on augmented Lagrangian method显示文摘 | REN Dongwei ZUO Wangmeng ZHAO Xiaofei | 2013 | Pattern Recognition Letters2013，34，2： | 1 |
| 14 | An as- sembled matrix distance metric for 2DPCA-based im- age recognition 显示文摘 | Zuo Wangmeng Zhang D Wang Kuanquan | 2006 | Pattern Recognition Letters2006，27，3： | 1 |
| 15 | An assembled matrix distance metric for 2DPCA-based image recognition 显示文摘 | Zuo Wangmeng Zhang David Wang Kuanquan | 2006 | Pattern Recognition Letters2006，27，1： | 1 |
| 16 | Supervised Sparse Represen-tation Method with a Heuristic Strategy and Face Recognition Experi-ments显示文摘 | Xu Yong Zuo Wangmeng Fan Zizhu | | 0，，01： | 1 |
| 17 | Self-Sparse Generative Adversarial Networks显示文摘Generative adversarial networks(GANs)are an unsupervised generative model that learns data distribution through adversarial training.However,recent experiments indicated that GANs are difficult to train due to the requirement of optimization in the high dimensional parameter space and the zero gradient problem.In this work,we propose a self-sparse generative adversarial network(Self-Sparse GAN)that reduces the parameter space and alleviates the zero gradient problem.In the Self-Sparse GAN,we design a self-adaptive sparse transform module(SASTM)comprising the sparsity decomposition and feature-map recombination,which can be applied on multi-channel feature maps to obtain sparse feature maps.The key idea of Self-Sparse GAN is to add the SASTM following every deconvolution layer in the generator,which can adaptively reduce the parameter space by utilizing the sparsity in multi-channel feature maps.We theoretically prove that the SASTM can not only reduce the search space of the convolution kernel weight of the generator but also alleviate the zero gradient problem by maintaining meaningful features in the batch normalization layer and driving the weight of deconvolution layers away from being negative.The experimental results show that our method achieves the best Fréchet inception distance(FID)scores for image generation compared with Wasserstein GAN with gradient penalty(WGAN-GP)on MNIST,Fashion-MNIST,CIFAR-10,STL-10,mini-ImageNet,CELEBA-HQ,and LSUN bedrooms datasets,and the relative decrease of FID is 4.76%-21.84%.Meanwhile,an architectural sketch dataset(Sketch)is also used to validate the superiority of the proposed method. | Wenliang Qian Yang Xu Wangmeng Zuo Hui Li | 2022 | CAAI Artificial Intelligence Research2022，1，1： | 0 |
| 18 | Metric Learning with Relative Distance Constraints:A Modified SVM Approach显示文摘Distance metric learning plays an important role in many machine learning tasks. In this paper, we propose a method for learning a Mahanalobis distance metric. By formulating the metric learning problem with relative distance constraints, we suggest a Relative Distance Constrained Metric Learning (RDCML) model which can be easily implemented and effectively solved by a modified support vector machine (SVM) approach. Experimental results on UCI datasets and handwritten digits datasets show that RDCML achieves better or comparable classification accuracy when compared with the state-of-the-art metric learning methods. | Changchun Luo Mu Li Hongzhi Zhang Faqiang Wang David Zhang Wangmeng Zuo | 2015 | 国际计算机前沿大会会议论文集2015，，1： | 0 |
| 19 | Survey on leveraging pre-trained generative adversarial networks for image editing and restoration显示文摘Generative adversarial networks(GANs)have drawn enormous attention due to their simple yet efective training mechanism and superior image generation quality.With the ability to generate photorealistic high-resolution(e.g.,1024×1024)images,recent GAN models have greatly narrowed the gaps between the generated images and the real ones.Therefore,many recent studies show emerging interest to take advantage of pre-trained GAN models by exploiting the well-disentangled latent space and the learned GAN priors.In this study,we briefly review recent progress on leveraging pre-trained large-scale GAN models from three aspects,i.e.,(1)the training of large-scale generative adversarial networks,(2)exploring and understanding the pre-trained GAN models,and(3)leveraging these models for subsequent tasks like image restoration and editing. | Ming LIU Yuxiang WEI Xiaohe WU Wangmeng ZUO Lei ZHANG | 2023 | Science China(Information Sciences)2023，66，5： | 0 |
您所在的机构暂未开通此部分的功能，请联系管理员