Zhixuan Li

Zhixuan Li

Auto-generated profile, based on publicly available information

Zhixuan Li

College of Computing and Data Science, Nanyang Technological University, Singapore

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
22 September 2023 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
ZLZhixuan Li
Zhixuan Li
WYWeining Ye
Weining Ye
TJTingting Jiang
Tingting Jiang
THTiejun Huang
Tiejun Huang
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
Verified
Book Chapter
Closed access
PDF file
ZLZhixuan Li
Zhixuan Li
WYWeining Ye
Weining Ye
TJTingting Jiang
Tingting Jiang
THTiejun Huang
Tiejun Huang

29 January 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
Yujia LiuYujia Liu
Yujia Liu
Dingquan LiDingquan Li
Dingquan Li
ZLZhixuan Li
Zhixuan Li
THTiejun Huang
Tiejun Huang
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.

16 October 2020 in arXiv
Verified
Preprint
Open access
PDF file
RSRuohua Shi
Ruohua Shi
WWWenyao Wang
Wenyao Wang
ZLZhixuan Li
Zhixuan Li
LHLiuyuan He
Liuyuan He
KSKaiwen Sheng
Kaiwen Sheng
THTiejun Huang
Tiejun Huang
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.