Deming Zhai

Deming Zhai

Auto-generated profile, based on publicly available information

Deming Zhai

Harbin Institute of Technology

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 February 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XZXiong Zhou
Xiong Zhou
XLXianming Liu
Xianming Liu
DZDeming Zhai
Deming Zhai
Junjun JiangJunjun Jiang
Junjun Jiang
XJXiangyang Ji
Xiangyang Ji
Supervised deep learning has achieved tremendous success in many computer vision tasks, which however is prone to overfit noisy labels. To mitigate the undesirable influence of noisy labels, robust loss functions offer a feasible approach to achieve noise-tolerant learning. In this work, we systematically study the problem of noise-tolerant learning with respect to both classification and regression. Specifically, we propose a new class of loss function, namely asymmetric loss functions (ALFs), which are tailored to satisfy the Bayes-optimal condition and thus are robust to noisy labels. For classification, we investigate general theoretical properties of ALFs on categorical noisy labels, and introduce the asymmetry ratio to measure the asymmetry of a loss function. We extend several commonly-used loss functions, and establish the necessary and sufficient conditions to make them asymmetric and thus noise-tolerant. For regression, we extend the concept of noise-tolerant learning for image restoration with continuous noisy labels. We theoretically prove that $\ell _{p}$ loss ( $p>0$ ) is noise-tolerant for targets with the additive white Gaussian noise. For targets with general noise, we introduce two losses as surrogates of $\ell _{0}$ loss that seeks the mode when clean pixels keep dominant. Experimental results demonstrate that ALFs can achieve better or comparative performance compared with the state-of-the-arts.

4 September 2017 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
DZDeming Zhai
Deming Zhai
XLXianming Liu
Xianming Liu
XJXiangyang Ji
Xiangyang Ji
DZDebin Zhao
Debin Zhao
SSShin'Ichi Satoh
Shin'Ichi Satoh
WGWen Gao
Wen Gao
Recent years have witnessed the growing popularity of hashing for large-scale multimedia retrieval. Extensive hashing methods have been designed for data stored in a single machine, $i.e., centralized$ $hashing$. In many real-world applications, however, the large-scale data is often distributed across different locations, servers or sites. Although hashing for distributed data can be implemented by assembling all distributed data together as a whole dataset in theory, it usually leads to prohibitive computation, communication, and storage costs in practice. Up to now, only very a few methods were tailored for $distributed$ $hashing$, which are all unsupervised approaches. In this paper, we propose an efficient and effective method called Supervised Distributed Hashing (SupDisH), which learns discriminative hash functions by leveraging the semantic label information in a distributed manner. Specifically, we cast the distributed hashing problem into the framework of classification, where the learned binary codes are expected to be distinctive enough for semantic retrieval. By introducing auxiliary variables, the distributed model is then separated into a set of decentralized subproblems with consistency constraints, which can be solved in parallel on each vertex of the distributed network. As such, we can obtain high quality distinctive unbiased binary codes and consistent hash functions with low computational complexity, which facilitate tackling large-scale multimedia retrieval tasks involving distributed datasets. Experimental evaluations on three large-scale datasets show that SupDisH is competitive to centralized hashing methods and outperforms the state-of-the-art unsupervised distributed method significantly.

13 July 2023 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
HWHanzhang Wang
Hanzhang Wang
DZDeming Zhai
Deming Zhai
XLXianming Liu
Xianming Liu
Junjun JiangJunjun Jiang
Junjun Jiang
WGWen Gao
Wen Gao
Exemplar-based colorization is a challenging task, which attempts to add colors to the target grayscale image with the aid of a reference color image, so as to keep the target semantic content while with the reference color style. In order to achieve visually plausible chromatic results, it is important to sufficiently exploit the global color style and the semantic color information of the reference color image. However, existing methods are either clumsy in exploiting the semantic color information, or lack of the dedicated fusion mechanism to decorate the target grayscale image with the reference semantic color information. Besides, these methods usually use a single-stage encoder-decoder architecture, which results in the loss of spatial details. To remedy these problems, we propose an effective exemplar colorization strategy based on pyramid dual non-local attention network to exploit the long-range dependency as well as multi-scale correlation. Specifically, two symmetrical branches of pyramid non-local attention block are tailored to achieve alignments from the target feature to the reference feature and from the reference feature to the target feature respectively. The bidirectional non-local fusion strategy is further applied to get a sufficient fusion feature that achieves full semantic consistency between multi-modal information. To train the network, we propose an unsupervised learning manner, which employs the hybrid supervision including the pseudo paired supervision from the reference color images and unpaired supervision from both the target grayscale and reference color images. Extensive experimental results are provided to demonstrate that our method achieves better photo-realistic colorization performance than the state-of-the-art methods. The source code is available at https://github.com/wd1511/PDNLA-Net.

1 January 2019 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
Yongbing ZhangYongbing Zhang
Yongbing Zhang
YFYihui Feng
Yihui Feng
XLXianming Liu
Xianming Liu
DZDeming Zhai
Deming Zhai
XJXiangyang Ji
Xiangyang Ji
QDQionghai Dai
Qionghai Dai
Depth images play an important role and are prevalently used in many computer vision and computational imaging tasks. However, due to the limitation of active sensing technology, the captured depth images in practice usually suffer from low resolution and noise, which prevents its further applications. To remedy this problem, in this paper, we firstly propose an adaptive data fidelity formulation to optimally generate each depth pixel from a mixture probability distribution, characterizing the similarity both in the depth map and the corresponding highresolution guided color image. The proposed method is able to fit the distribution of the input depth signal as an optimization problem by maximizing the mixture probability. Furthermore, to promote the piecewise property that depth images exhibit, we propose a transferred graph Laplacian model as a regularization term, which is general and able to handle various depth recovery tasks well, such as super-resolution and denoising. Specifically, each pixel within the recovered depth image is represented as a vertex in a graph with weights in connected edges representing the similarity between vertices. By minimizing the squared variations of the image signal, the task of depth image recovery can be converted to the problem of graph based image filtering. Since the proposed graph Laplacian regularization model is able to fully exploit a priori information about the depth image, a much more accurate and robust estimation of the underlying depth can be obtained. Extensive experiment evaluations verify that the proposed method obtains recovered depth with higher quality in terms of both objective and subjective criteria, compared with most state-of-the-art methods.

22 June 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
WZWenbo Zhao
Wenbo Zhao
XLXianming Liu
Xianming Liu
DZDeming Zhai
Deming Zhai
Junjun JiangJunjun Jiang
Junjun Jiang
XJXiangyang Ji
Xiangyang Ji
Point clouds upsampling (PCU), which aims to generate dense and uniform point clouds from the captured sparse input of 3D sensor such as LiDAR, is a practical yet challenging task. It has potential applications in many real-world scenarios, such as autonomous driving, robotics, AR/VR, etc. Deep neural network based methods achieve remarkable success in PCU. However, most existing deep PCU methods either take the end-to-end supervised training, where large amounts of pairs of sparse input and dense ground-truth are required to serve as the supervision; or treat up-scaling of different factors as independent tasks, where multiple networks are required for different scaling factors, leading to significantly increased model complexity and training time. In this paper, we propose a novel method that achieves self-supervised and magnification-flexible PCU simultaneously. No longer explicitly learning the mapping between sparse and dense point clouds, we formulate PCU as the task of seeking nearest projection points on the implicit surface for seed points. We then define two implicit neural functions to estimate projection direction and distance respectively, which can be trained by the pretext learning tasks. Moreover, the projection rectification strategy is tailored to remove outliers so as to keep the shape of object clear and sharp. Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than state-of-the-art supervised methods. The source code of our method can be found in https://github.com/xnowbzhao/PU-SSAS/ .

1 January 2010
Verified
Conference Paper
Closed access
DZDeming Zhai
Deming Zhai
BLBo Li
Bo Li
HCHong Chang
Hong Chang
SSShiguang Shan
Shiguang Shan
XCXilin Chen
Xilin Chen
WGWen Gao
Wen Gao