Zhixuan Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Zhixuan Li has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Tiejun Huang
Peking University
3 shared publications - Tingting Jiang
National Engineering Research Center of Visual Technology, State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China
3 shared publications - Weining Ye
National Engineering Research Center of Visual Technology, National Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China
2 shared publications - Yujia Liu
National Engineering Research Center of Visual Technology, State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University, Beijing, China
2 shared publications - Chen Hui
Nanjing University of Information Science and Technology, Nanjing, Jiangsu, China
1 shared publication - Chenyue Song
Harbin Institute of Technology, Harbin, Heilongjiang, China
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5768-5777
Single Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentation
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 5768-5777
Open AccessSingle Point, Full Mask: Velocity-Guided Level Set Evolution for End-to-End Amodal Segmentation
- 29 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (6) , 6660-6672
SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack Against No-Reference Image Quality Assessment Models
No-Reference Image Quality Assessment (NR-IQA) models play an important role in various real-world applications. Recently, adversarial attacks against NR-IQA models have attracted increasing attention, as they provide valuable insights for revealing model vulnerabilities and guiding robust system design. Some effective attacks have been proposed against NR-IQA models in white-box settings, where the attacker has full access to the target model. However, these attacks often suffer from poor transferability to unknown target models in more realistic black-box scenarios, where the target model is inaccessible. This work makes the first attempt to address the challenge of low transferability in attacking NR-IQA models by proposing a transferable Signed Ensemble Gaussian black-box Attack (SEGA). The main idea is to approximate the gradient of the target model by applying Gaussian smoothing to source models and ensembling their smoothed gradients. To ensure the imperceptibility of adversarial perturbations, SEGA further removes inappropriate perturbations using a specially designed perturbation filter mask. Experimental results demonstrate the superior transferability of SEGA, validating its effectiveness in enabling successful transfer-based black-box attacks against NR-IQA models.
- 29 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 48 (6) , 6660-6672
SEGA: A Transferable Signed Ensemble Gaussian Black-Box Attack Against No-Reference Image Quality Assessment Models
No-Reference Image Quality Assessment (NR-IQA) models play an important role in various real-world applications. Recently, adversarial attacks against NR-IQA models have attracted increasing attention, as they provide valuable insights for revealing model vulnerabilities and guiding robust system design. Some effective attacks have been proposed against NR-IQA models in white-box settings, where the attacker has full access to the target model. However, these attacks often suffer from poor transferability to unknown target models in more realistic black-box scenarios, where the target model is inaccessible. This work makes the first attempt to address the challenge of low transferability in attacking NR-IQA models by proposing a transferable Signed Ensemble Gaussian black-box Attack (SEGA). The main idea is to approximate the gradient of the target model by applying Gaussian smoothing to source models and ensembling their smoothed gradients. To ensure the imperceptibility of adversarial perturbations, SEGA further removes inappropriate perturbations using a specially designed perturbation filter mask. Experimental results demonstrate the superior transferability of SEGA, validating its effectiveness in enabling successful transfer-based black-box attacks against NR-IQA models.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 3924-3936
GIN: Generative INvariant Shape Prior for Amodal Instance Segmentation
Amodal instance segmentation (AIS) predicts the complete shape of the occluded object, including both visible and occluded regions. Because visual clues are lacking, the occluded region is difficult to segment accurately. In human amodal perception, shape-prior knowledge is helpful for AIS. The previous method uses a 2D shape prior by rote memorizing , establishing a shape dictionary and retrieving the closest mask to the segmentation result. However, this approach cannot obtain the shape prior, which is not prestored in the shape dictionary. In this paper, to improve generalization ability, we propose a generative invariant shape-prior network (GIN), simulating the human perception process that learns the basic shape, which is invariant to transformations, including translation, rotation, and scaling. We design a novel framework that decouples the learning of shape priors from transformation . GIN is end-to-end trainable and needs no dictionary establishment, making the whole pipeline efficient. GIN outperforms state-of-the-art methods on three public datasets (D2SA, COCOA-cls, and KINS) with large margins.
- 22 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 26 (15209210) , 3924-3936
GIN: Generative INvariant Shape Prior for Amodal Instance Segmentation
Amodal instance segmentation (AIS) predicts the complete shape of the occluded object, including both visible and occluded regions. Because visual clues are lacking, the occluded region is difficult to segment accurately. In human amodal perception, shape-prior knowledge is helpful for AIS. The previous method uses a 2D shape prior by rote memorizing , establishing a shape dictionary and retrieving the closest mask to the segmentation result. However, this approach cannot obtain the shape prior, which is not prestored in the shape dictionary. In this paper, to improve generalization ability, we propose a generative invariant shape-prior network (GIN), simulating the human perception process that learns the basic shape, which is invariant to transformations, including translation, rotation, and scaling. We design a novel framework that decouples the learning of shape priors from transformation . GIN is end-to-end trainable and needs no dictionary establishment, making the whole pipeline efficient. GIN outperforms state-of-the-art methods on three public datasets (D2SA, COCOA-cls, and KINS) with large margins.
- 22 October 2022
- Published by Springer Nature
- p. 165-181
2D Amodal Instance Segmentation Guided by 3D Shape Prior
- 22 October 2022
- Published by Springer Nature
- p. 165-181
2D Amodal Instance Segmentation Guided by 3D Shape Prior
- Open Access
Human Perception-based Evaluation Criterion for Ultra-high Resolution Cell Membrane Segmentation
Computer vision technology is widely used in biological and medical data analysis and understanding. However, there are still two major bottlenecks in the field of cell membrane segmentation, which seriously hinder further research: lack of sufficient high-quality data and lack of suitable evaluation criteria. In order to solve these two problems, this paper first proposes an Ultra-high Resolution Image Segmentation dataset for the Cell membrane, called U-RISC, the largest annotated Electron Microscopy (EM) dataset for the Cell membrane with multiple iterative annotations and uncompressed high-resolution raw data. During the analysis process of the U-RISC, we found that the current popular segmentation evaluation criteria are inconsistent with human perception. This interesting phenomenon is confirmed by a subjective experiment involving twenty people. Furthermore, to resolve this inconsistency, we propose a new evaluation criterion called Perceptual Hausdorff Distance (PHD) to measure the quality of cell membrane segmentation results. Detailed performance comparison and discussion of classic segmentation methods along with two iterative manual annotation results under existing evaluation criteria and PHD is given.
Open AccessHuman Perception-based Evaluation Criterion for Ultra-high Resolution Cell Membrane Segmentation
Computer vision technology is widely used in biological and medical data analysis and understanding. However, there are still two major bottlenecks in the field of cell membrane segmentation, which seriously hinder further research: lack of sufficient high-quality data and lack of suitable evaluation criteria. In order to solve these two problems, this paper first proposes an Ultra-high Resolution Image Segmentation dataset for the Cell membrane, called U-RISC, the largest annotated Electron Microscopy (EM) dataset for the Cell membrane with multiple iterative annotations and uncompressed high-resolution raw data. During the analysis process of the U-RISC, we found that the current popular segmentation evaluation criteria are inconsistent with human perception. This interesting phenomenon is confirmed by a subjective experiment involving twenty people. Furthermore, to resolve this inconsistency, we propose a new evaluation criterion called Perceptual Hausdorff Distance (PHD) to measure the quality of cell membrane segmentation results. Detailed performance comparison and discussion of classic segmentation methods along with two iterative manual annotation results under existing evaluation criteria and PHD is given.