Zenglin Shi

Zenglin Shi

Auto-generated profile, based on publicly available information

Zenglin Shi

Hefei University of Technology, Hefei, China

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
26 September 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LZLe Zhang
Le Zhang
ZSZenglin Shi
Zenglin Shi
MCMing-Ming Cheng
Ming-Ming Cheng
YLYun Liu
Yun Liu
JBJia-Wang Bian
Jia-Wang Bian
ZZZeng Zeng
Zeng Zeng
Nonlinear regression has been extensively employed in many computer vision problems (e.g., crowd counting, age estimation, affective computing). Under the umbrella of deep learning, two common solutions exist i) transforming nonlinear regression to a robust loss function which is jointly optimizable with the deep convolutional network, and ii) utilizing ensemble of deep networks. Although some improved performance is achieved, the former may be lacking due to the intrinsic limitation of choosing a single hypothesis and the latter usually suffers from much larger computational complexity. To cope with those issues, we propose to regress via an efficient "divide and conquer" manner. The core of our approach is the generalization of negative correlation learning that has been shown, both theoretically and empirically, to work well for non-deep regression problems. Without extra parameters, the proposed method controls the bias-variance-covariance trade-off systematically and usually yields a deep regression ensemble where each base model is both "accurate" and "diversified." Moreover, we show that each sub-problem in the proposed method has less Rademacher Complexity and thus is easier to optimize. Extensive experiments on several diverse and challenging tasks including crowd counting, personality analysis, age estimation, and image super-resolution demonstrate the superiority over challenging baselines.

11 February 2022 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
ZSZenglin Shi
Zenglin Shi
PMPascal Mettes
Pascal Mettes
SMSubhransu Maji
Subhransu Maji
CSCees G. M. Snoek
Cees G. M. Snoek
The deep image prior showed that a randomly initialized network with a suitable architecture can be trained to solve inverse imaging problems by simply optimizing it’s parameters to reconstruct a single degraded image. However, it suffers from two practical limitations. First, it remains unclear how to control the prior beyond the choice of the network architecture. Second, training requires an oracle stopping criterion as during the optimization the performance degrades after reaching an optimum value. To address these challenges we introduce a frequency-band correspondence measure to characterize the spectral bias of the deep image prior, where low-frequency image signals are learned faster and better than high-frequency counterparts. Based on our observations, we propose techniques to prevent the eventual performance degradation and accelerate convergence. We introduce a Lipschitz-controlled convolution layer and a Gaussian-controlled upsampling layer as plug-in replacements for layers used in the deep architectures. The experiments show that with these changes the performance does not degrade during optimization, relieving us from the need for an oracle stopping criterion. We further outline a stopping criterion to avoid superfluous computation. Finally, we show that our approach obtains favorable results compared to current approaches across various denoising, deblocking, inpainting, super-resolution and detail enhancement tasks. Code is available at https://github.com/shizenglin/Measure-and-Control-Spectral-Bias.

27 August 2021 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
ZSZenglin Shi
Zenglin Shi
YCYunlu Chen
Yunlu Chen
EGEfstratios Gavves
Efstratios Gavves
PMPascal Mettes
Pascal Mettes
CSCees G. M. Snoek
Cees G. M. Snoek
The goal of this paper is guided image filtering, which emphasizes the importance of structure transfer during filtering by means of an additional guidance image. Where classical guided filters transfer structures using hand-designed functions, recent guided filters have been considerably advanced through parametric learning of deep networks. The state-of-the-art leverages deep networks to estimate the two core coefficients of the guided filter. In this work, we posit that simultaneously estimating both coefficients is suboptimal, resulting in halo artifacts and structure inconsistencies. Inspired by unsharp masking, a classical technique for edge enhancement that requires only a single coefficient, we propose a new and simplified formulation of the guided filter. Our formulation enjoys a filtering prior from a low-pass filter and enables explicit structure transfer by estimating a single coefficient. Based on our proposed formulation, we introduce a successive guided filtering network, which provides multiple filtering results from a single network, allowing for a trade-off between accuracy and efficiency. Extensive ablations, comparisons and analysis show the effectiveness and efficiency of our formulation and network, resulting in state-of-the-art results across filtering tasks like upsampling, denoising, and cross-modality filtering. Code is available at https://github.com/shizenglin/Unsharp-Mask-Guided-Filtering.

21 October 2020 in IEEE Transactions on Cybernetics
Verified
Journal Article
Closed access
SHShizhe Hu
Shizhe Hu
ZSZenglin Shi
Zenglin Shi
YYYangdong Ye
Yangdong Ye
Multiview clustering (MVC) has recently been the focus of much attention due to its ability to partition data from multiple views via view correlations. However, most MVC methods only learn either interfeature correlations or intercluster correlations, which may lead to unsatisfactory clustering performance. To address this issue, we propose a novel dual-correlated multivariate information bottleneck (DMIB) method for MVC. DMIB is able to explore both interfeature correlations (the relationship among multiple distinct feature representations from different views) and intercluster correlations (the close agreement among clustering results obtained from individual views). For the former, we integrate both view-shared feature correlations discovered by learning a shared discriminative feature subspace and view-specific feature information to fully explore the interfeature correlation. This allows us to attain multiple reliable local clustering results of different views. Following this, we explore the intercluster correlations by learning the shared mutual information over different local clusterings for an improved global partition. By integrating both correlations, we formulate the problem as a unified information maximization function and further design a two-step method for optimization. Moreover, we theoretically prove the convergence of the proposed algorithm, and discuss the relationships between our method and several existing clustering paradigms. The experimental results on multiple datasets demonstrate the superiority of DMIB compared to several state-of-the-art clustering methods.

2 July 2018 in IEEE Transactions on Industrial Informatics
Verified
Journal Article
Closed access
ZSZenglin Shi
Zenglin Shi
LZLe Zhang
Le Zhang
YSYibo Sun
Yibo Sun
YYYangdong Ye
Yangdong Ye
CNNS reign undisputed as the new de-facto method for computer vision tasks owning to their success in visual recognition task on still images. However, their adaptations to crowd counting have not clearly established their superiority over shallow models. Existing CNNs turn out to be self-limiting in challenging scenarios for crowd counting because of their shallow structure. In this work, we introduce a dynamic augmentation technique to train a much deeper CNN for crowd counting. In order to decrease over-fitting caused by limited number of training samples, multitask learning is further employed to learn generalisable representations across similar domains. We also propose to aggregate multi-scale convolutional features extracted from the entire image into a compact single vector representation amenable to efficient and accurate counting by way of "Vector of Locally Aggregated Descriptors" (VLAD). The "deeply supervised" strategy is employed to provide additional supervision signal for bottom layers for further performance improvement.

25 April 2024 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
YLYimin Luo
Yimin Luo
QYQinyu Yang
Qinyu Yang
ZLZiyi Liu
Ziyi Liu
ZSZenglin Shi
Zenglin Shi
WHWeimin Huang
Weimin Huang
JCJun Cheng
Jun Cheng
In a clinical setting, the acquisition of certain medical image modality is often unavailable due to various considerations such as cost, radiation, etc. Therefore, unpaired cross-modality translation techniques, which involve training on the unpaired data and synthesizing the target modality with the guidance of the acquired source modality, are of great interest. Previous methods for synthesizing target medical images are to establish one-shot mapping through generative adversarial networks (GANs). As promising alternatives to GANs, diffusion models have recently received wide interests in generative tasks. In this paper, we propose a target-guided diffusion model (TGDM) for unpaired cross-modality medical image translation. For training, to encourage our diffusion model to learn more visual concepts, we adopted a perception prioritized weight scheme (P2W) to the training objectives. For sampling, a pre-trained classifier is adopted in the reverse process to relieve modality-specific remnants from source data. Experiments on both brain MRI-CT and prostate MRI-US datasets demonstrate that the proposed method achieves a visually realistic result that mimics a vivid anatomical section of the target organ. In addition, we have also conducted a subjective assessment based on the synthesized samples to further validate the clinical value of TGDM.