Zhiqun Zhao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Zhiqun Zhao has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Hao Sun
Video Processing and Communication Laboratory, Department of Electrical and Computer Engineering, University of Missouri, Columbia, USA
5 shared publications Zhihai He
University of Missouri,Department of Electrical Engineering and Computer Science,Columbia,MO,USA,65211
5 shared publications- Hengyou Wang
School of Science, Beijing University of Civil Engineering and Architecture, Beijing, China
3 shared publications - Gang Fang
UnionStrong (Beijing) Technology Co., Ltd., Beijing, China
1 shared publication - Guangming Yang
UnionStrong (Beijing) Technology Co., Ltd., Beijing, China
1 shared publication - Hailan Jin
UnionStrong (Beijing) Technology Co., Ltd., Beijing, China
1 shared publication
Latest Publications
- Open Access
- 10 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 187-194
Aneurysm Vessel 3D Reconstruction from Multi-View 2D Images via Fine-Tuned 3D Generative Model with Optimized Inference
- 10 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 187-194
Open AccessAneurysm Vessel 3D Reconstruction from Multi-View 2D Images via Fine-Tuned 3D Generative Model with Optimized Inference
- 5 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Structure-Oriented Progressive Low-Rank Image Restoration for Defending Adversarial Attacks
Deep neural networks recognize objects by analyzing local image details and summarizing their information along the inference layers to derive the final decision. Because of this, they are prone to adversarial attacks. On the other hand, human eyes recognize objects based on their global structures and semantic cues, instead of local image textures. In this work, we propose to develop a structure-oriented progressive low-rank image completion method to remove unneeded texture details from the input images and shift the bias of deep neural networks towards global object structures and semantic cues. We formulate the problem into a low-rank matrix completion problem with progressively smoothed rank functions to avoid local minimums. Our experimental results demonstrate the proposed method is able to successfully remove the insignificant local image details while preserving important global object structures.
- 5 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Structure-Oriented Progressive Low-Rank Image Restoration for Defending Adversarial Attacks
Deep neural networks recognize objects by analyzing local image details and summarizing their information along the inference layers to derive the final decision. Because of this, they are prone to adversarial attacks. On the other hand, human eyes recognize objects based on their global structures and semantic cues, instead of local image textures. In this work, we propose to develop a structure-oriented progressive low-rank image completion method to remove unneeded texture details from the input images and shift the bias of deep neural networks towards global object structures and semantic cues. We formulate the problem into a low-rank matrix completion problem with progressively smoothed rank functions to avoid local minimums. Our experimental results demonstrate the proposed method is able to successfully remove the insignificant local image details while preserving important global object structures.
- 10 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 6485-6497
Removing Adversarial Noise via Low-Rank Completion of High-Sensitivity Points
Deep neural networks are fragile under adversarial attacks. In this work, we propose to develop a new defense method based on image restoration to remove adversarial attack noise. Using the gradient information back-propagated over the network to the input image, we identify high-sensitivity keypoints which have significant contributions to the image classification performance. We then partition the image pixels into the two groups: high-sensitivity and low-sensitivity points. For low-sensitivity pixels, we use a total variation (TV) norm-based image smoothing method to remove adversarial attack noise. For those high-sensitivity keypoints, we develop a structure-preserving low-rank image completion method. Based on matrix analysis and optimization, we derive an iterative solution for this optimization problem. Our extensive experimental results on the CIFAR-10, SVHN, and Tiny-ImageNet datasets have demonstrated that our method significantly outperforms other defense methods which are based on image de-noising or restoration, especially under powerful adversarial attacks.
- 10 June 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 6485-6497
Removing Adversarial Noise via Low-Rank Completion of High-Sensitivity Points
Deep neural networks are fragile under adversarial attacks. In this work, we propose to develop a new defense method based on image restoration to remove adversarial attack noise. Using the gradient information back-propagated over the network to the input image, we identify high-sensitivity keypoints which have significant contributions to the image classification performance. We then partition the image pixels into the two groups: high-sensitivity and low-sensitivity points. For low-sensitivity pixels, we use a total variation (TV) norm-based image smoothing method to remove adversarial attack noise. For those high-sensitivity keypoints, we develop a structure-preserving low-rank image completion method. Based on matrix analysis and optimization, we derive an iterative solution for this optimization problem. Our extensive experimental results on the CIFAR-10, SVHN, and Tiny-ImageNet datasets have demonstrated that our method significantly outperforms other defense methods which are based on image de-noising or restoration, especially under powerful adversarial attacks.
- 27 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (3) , 1483-1497
Reciprocal Twin Networks for Pedestrian Motion Learning and Future Path Prediction
Modeling the moving behaviors and predicting the future paths of pedestrians, especially for those in complex scenes, remain a challenging problem in machine learning. We recognize that human motion trajectories, governed by social norms and constrained by physical structures of the surrounding environment, are both forward predictable and backward predictable. Motivated by this observation, we develop a new approach, called reciprocal twin networks , for human trajectory learning and prediction. We design two networks, a forward prediction network to predict future trajectory from past observations and a backward prediction that performs the trajectory prediction backward in time. The backward prediction network serves as the inverse operation of the forward prediction network, forming a reciprocal constraint. During the training stage, this reciprocal constraint allows them to be jointly learned for accurate and robust human trajectory prediction. During the inference stage, we borrow the concept of adversarial attack of deep neural networks, which iteratively modifies the input of the network to match the given or forced network output, and develop a new method, called reciprocal attack for matched prediction , to achieve accurate human trajectory prediction. Our experimental results on benchmark datasets demonstrate that our new method outperforms the state-of-the-art methods for human trajectory prediction.
- 27 April 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 32 (3) , 1483-1497
Reciprocal Twin Networks for Pedestrian Motion Learning and Future Path Prediction
Modeling the moving behaviors and predicting the future paths of pedestrians, especially for those in complex scenes, remain a challenging problem in machine learning. We recognize that human motion trajectories, governed by social norms and constrained by physical structures of the surrounding environment, are both forward predictable and backward predictable. Motivated by this observation, we develop a new approach, called reciprocal twin networks , for human trajectory learning and prediction. We design two networks, a forward prediction network to predict future trajectory from past observations and a backward prediction that performs the trajectory prediction backward in time. The backward prediction network serves as the inverse operation of the forward prediction network, forming a reciprocal constraint. During the training stage, this reciprocal constraint allows them to be jointly learned for accurate and robust human trajectory prediction. During the inference stage, we borrow the concept of adversarial attack of deep neural networks, which iteratively modifies the input of the network to match the given or forced network output, and develop a new method, called reciprocal attack for matched prediction , to achieve accurate human trajectory prediction. Our experimental results on benchmark datasets demonstrate that our new method outperforms the state-of-the-art methods for human trajectory prediction.
- Open Access
Structure-Preserving Progressive Low-rank Image Completion for Defending Adversarial Attacks
Deep neural networks recognize objects by analyzing local image details and summarizing their information along the inference layers to derive the final decision. Because of this, they are prone to adversarial attacks. Small sophisticated noise in the input images can accumulate along the network inference path and produce wrong decisions at the network output. On the other hand, human eyes recognize objects based on their global structure and semantic cues, instead of local image textures. Because of this, human eyes can still clearly recognize objects from images which have been heavily damaged by adversarial attacks. This leads to a very interesting approach for defending deep neural networks against adversarial attacks. In this work, we propose to develop a structure-preserving progressive low-rank image completion (SPLIC) method to remove unneeded texture details from the input images and shift the bias of deep neural networks towards global object structures and semantic cues. We formulate the problem into a low-rank matrix completion problem with progressively smoothed rank functions to avoid local minimums during the optimization process. Our experimental results demonstrate that the proposed method is able to successfully remove the insignificant local image details while preserving important global object structures. On black-box, gray-box, and white-box attacks, our method outperforms existing defense methods (by up to 12.6%) and significantly improves the adversarial robustness of the network.
Open AccessStructure-Preserving Progressive Low-rank Image Completion for Defending Adversarial Attacks
Deep neural networks recognize objects by analyzing local image details and summarizing their information along the inference layers to derive the final decision. Because of this, they are prone to adversarial attacks. Small sophisticated noise in the input images can accumulate along the network inference path and produce wrong decisions at the network output. On the other hand, human eyes recognize objects based on their global structure and semantic cues, instead of local image textures. Because of this, human eyes can still clearly recognize objects from images which have been heavily damaged by adversarial attacks. This leads to a very interesting approach for defending deep neural networks against adversarial attacks. In this work, we propose to develop a structure-preserving progressive low-rank image completion (SPLIC) method to remove unneeded texture details from the input images and shift the bias of deep neural networks towards global object structures and semantic cues. We formulate the problem into a low-rank matrix completion problem with progressively smoothed rank functions to avoid local minimums during the optimization process. Our experimental results demonstrate that the proposed method is able to successfully remove the insignificant local image details while preserving important global object structures. On black-box, gray-box, and white-box attacks, our method outperforms existing defense methods (by up to 12.6%) and significantly improves the adversarial robustness of the network.
- 1 August 2020
- Published by Elsevier in Neurocomputing
- Vol. 400, 216-226
-norm low-rank linear approximation for accelerating deep neural networks- 1 August 2020
- Published by Elsevier in Neurocomputing
- Vol. 400, 216-226
-norm low-rank linear approximation for accelerating deep neural networks- 25 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 23 (15209210) , 1354-1366
Snowball: Iterative Model Evolution and Confident Sample Discovery for Semi-Supervised Learning on Very Small Labeled Datasets
In this work, we develop a joint sample discovery and iterative model evolution method for semi-supervised learning on very small labeled training sets. We propose a master-teacher-student model framework to provide multi-layer guidance during the model evolution process with multiple iterations and generations. The teacher model is constructed by performing an exponential moving average of the student models obtained from past training steps. The master network combines the knowledge of the student and teacher models with additional access to newly discovered samples. The master and teacher models are then used to guide the training of the student network by enforcing the consistency between their predictions of unlabeled samples and evolve all models when more and more samples are discovered. Our extensive experiments demonstrate that the process of discovering confident samples from the unlabeled dataset, once coupled with the master-teacher-student network evolution, can significantly improve the overall semi-supervised learning performance. For example, on the CIFAR-10 dataset, with a small set of 250 labeled samples, our method achieves an error rate of 11.58%, more than 38% lower than Mean-Teacher (49.91%). When coupled with the MixMatch augmentation and loss function, the improvements are also significant.
- 25 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 23 (15209210) , 1354-1366
Snowball: Iterative Model Evolution and Confident Sample Discovery for Semi-Supervised Learning on Very Small Labeled Datasets
In this work, we develop a joint sample discovery and iterative model evolution method for semi-supervised learning on very small labeled training sets. We propose a master-teacher-student model framework to provide multi-layer guidance during the model evolution process with multiple iterations and generations. The teacher model is constructed by performing an exponential moving average of the student models obtained from past training steps. The master network combines the knowledge of the student and teacher models with additional access to newly discovered samples. The master and teacher models are then used to guide the training of the student network by enforcing the consistency between their predictions of unlabeled samples and evolve all models when more and more samples are discovered. Our extensive experiments demonstrate that the process of discovering confident samples from the unlabeled dataset, once coupled with the master-teacher-student network evolution, can significantly improve the overall semi-supervised learning performance. For example, on the CIFAR-10 dataset, with a small set of 250 labeled samples, our method achieves an error rate of 11.58%, more than 38% lower than Mean-Teacher (49.91%). When coupled with the MixMatch augmentation and loss function, the improvements are also significant.