Wei Liu
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
Wei Liu has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Xiaodong Yue
Shanghai University
7 shared publications - Yufei Chen
Tongji University
4 shared publications - Jie Shi
School of Computer Engineering and Science, Shanghai University, Shanghai, China
2 shared publications - Zihao Li
Shanghai University
2 shared publications Ao Yang
School of Medicine, Shanghai University, Shanghai, China
1 shared publicationBan Long
Department of Physics, Capital Normal University, Beijing 100037
1 shared publication
Latest Publications
- 9 July 2026
- Published by Springer Nature
- p. 126-141
Beyond Statistical Divergence: A Hybrid Calibration Framework for Decoupling Hallucination in Large Language Models
- 9 July 2026
- Published by Springer Nature
- p. 126-141
Beyond Statistical Divergence: A Hybrid Calibration Framework for Decoupling Hallucination in Large Language Models
- 10 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Evidential Prior Guided Neural Collapse for Open World Object Detection
Open World Object Detection (OWOD) faces a fundamental dilemma: maintaining a stable representation for known classes while reserving flexible space for discovering unknown objects. Existing methods, while improving recall, often fail to assign discriminative confidence scores to unknown instances, resulting in critically low Average Precision (U-AP) and representation degradation during incremental learning. To remedy this, we propose the Evidential Prior Guided Neural Collapse (ENC) framework. ENC unifies representation learning and uncertainty quantification via a Geometric-Evidence Coupling mechanism. Unlike previous approaches, we map evidential support directly to the angular alignment with Simplex Equiangular Tight Frame (ETF) prototypes. Theoretically, the evidential prior functions as a geometric regularizer: it maximizes equiangular separation for confident known samples, while constraining ambiguous queries to approximate an isotropic uniform distribution via distributional regularization. Furthermore, to mitigate decision conflicts in self-supervised learning, we propose a dissonance-aware objectness optimization strategy that mines informative samples near the decision boundary. Extensive experiments on M-OWODB and S-OWODB benchmarks demonstrate that ENC sets a new state-of-the-art. Notably, it achieves a significant improvement in unknown class discovery, boosting U-AP from ≈ 1% to 9.2%, while exhibiting superior robustness against catastrophic forgetting in challenging incremental scenarios.
- 10 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Evidential Prior Guided Neural Collapse for Open World Object Detection
Open World Object Detection (OWOD) faces a fundamental dilemma: maintaining a stable representation for known classes while reserving flexible space for discovering unknown objects. Existing methods, while improving recall, often fail to assign discriminative confidence scores to unknown instances, resulting in critically low Average Precision (U-AP) and representation degradation during incremental learning. To remedy this, we propose the Evidential Prior Guided Neural Collapse (ENC) framework. ENC unifies representation learning and uncertainty quantification via a Geometric-Evidence Coupling mechanism. Unlike previous approaches, we map evidential support directly to the angular alignment with Simplex Equiangular Tight Frame (ETF) prototypes. Theoretically, the evidential prior functions as a geometric regularizer: it maximizes equiangular separation for confident known samples, while constraining ambiguous queries to approximate an isotropic uniform distribution via distributional regularization. Furthermore, to mitigate decision conflicts in self-supervised learning, we propose a dissonance-aware objectness optimization strategy that mines informative samples near the decision boundary. Extensive experiments on M-OWODB and S-OWODB benchmarks demonstrate that ENC sets a new state-of-the-art. Notably, it achieves a significant improvement in unknown class discovery, boosting U-AP from ≈ 1% to 9.2%, while exhibiting superior robustness against catastrophic forgetting in challenging incremental scenarios.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (2) , 2290-2303
Enhancing Reliability in Medical Image Classification of Imperfect Views
The fusion of multi-view medical images through deep neural networks is essential for boosting diagnostic precision in the field of medical image analysis. However, the reliability of these diagnostic results is often compromised by imperfections in image views, manifested as noise, artifacts, and data deficits arising from inconsistent diagnostic frequencies. These issues introduce a significant risk when merging medical views in a clinical setting. To address these problems, we introduce the Reliability-Enhanced Multi-view Network (REMNet), a novel framework designed to tackle two critical challenges: 1) reducing misclassification and uncertainty from imperfect view integration, and 2) improving the reliability and interpretability of multi-view medical image predictions. Specifically, REMNet merges information from multiple views into a coherent evidence framework and incorporates a Dirichlet prior within our predictive model to more accurately estimate confidence in predictions. Coupled with a robust fusion strategy and a precise confidence calibration process, REMNet consolidates the diverse strengths of various medical imaging views, reduces the impact of view imperfections, and enhances the reliability of medical imaging diagnostics. The superiority of REMNet is validated through comprehensive theoretical analysis and empirical experiments on multi-view medical image datasets across different modalities.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (2) , 2290-2303
Enhancing Reliability in Medical Image Classification of Imperfect Views
The fusion of multi-view medical images through deep neural networks is essential for boosting diagnostic precision in the field of medical image analysis. However, the reliability of these diagnostic results is often compromised by imperfections in image views, manifested as noise, artifacts, and data deficits arising from inconsistent diagnostic frequencies. These issues introduce a significant risk when merging medical views in a clinical setting. To address these problems, we introduce the Reliability-Enhanced Multi-view Network (REMNet), a novel framework designed to tackle two critical challenges: 1) reducing misclassification and uncertainty from imperfect view integration, and 2) improving the reliability and interpretability of multi-view medical image predictions. Specifically, REMNet merges information from multiple views into a coherent evidence framework and incorporates a Dirichlet prior within our predictive model to more accurately estimate confidence in predictions. Coupled with a robust fusion strategy and a precise confidence calibration process, REMNet consolidates the diverse strengths of various medical imaging views, reduces the impact of view imperfections, and enhances the reliability of medical imaging diagnostics. The superiority of REMNet is validated through comprehensive theoretical analysis and empirical experiments on multi-view medical image datasets across different modalities.
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7278-7287
Building Trust in Decision with Conformalized Multi-view Deep Classification
Uncertainty-aware multi-view deep classification methods have markedly improved the reliability of results amidst the challenges posed by noisy multi-view data, primarily by quantifying the uncertainty of predictions. Despite their efficacy, these methods encounter limitations in real-world applications: 1) They are limited to providing a single class prediction per instance, which can lead to inaccuracies when dealing with samples that are difficult to classify due to inconsistencies across multiple views. 2) While these methods offer a quantification of prediction uncertainty, the magnitude of such uncertainty often varies with different datasets, leading to confusion among decision-makers due to the lack of a standardized measure for uncertainty intensity. To address these issues, we introduce Conformalized Multi-view Deep Classification (CMDC), a novel method that generates set-valued rather than single-valued predictions and integrates uncertain predictions as an explicit class category. Through end-to-end training, CMDC minimizes the size of prediction sets while guaranteeing that the set-valued predictions contain the true label with a user-defined probability, building trust in decision-making. The superiority of CMDC is validated through comprehensive theoretical analysis and empirical experiments on various multi-view datasets.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 7278-7287
Open AccessBuilding Trust in Decision with Conformalized Multi-view Deep Classification
Uncertainty-aware multi-view deep classification methods have markedly improved the reliability of results amidst the challenges posed by noisy multi-view data, primarily by quantifying the uncertainty of predictions. Despite their efficacy, these methods encounter limitations in real-world applications: 1) They are limited to providing a single class prediction per instance, which can lead to inaccuracies when dealing with samples that are difficult to classify due to inconsistencies across multiple views. 2) While these methods offer a quantification of prediction uncertainty, the magnitude of such uncertainty often varies with different datasets, leading to confusion among decision-makers due to the lack of a standardized measure for uncertainty intensity. To address these issues, we introduce Conformalized Multi-view Deep Classification (CMDC), a novel method that generates set-valued rather than single-valued predictions and integrates uncertain predictions as an explicit class category. Through end-to-end training, CMDC minimizes the size of prediction sets while guaranteeing that the set-valued predictions contain the true label with a user-defined probability, building trust in decision-making. The superiority of CMDC is validated through comprehensive theoretical analysis and empirical experiments on various multi-view datasets.
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (11) , 3990-4003
Deep Closing: Enhancing Topological Connectivity in Medical Tubular Segmentation
Accurately segmenting tubular structures, such as blood vessels or nerves, holds significant clinical implications across various medical applications. However, existing methods often exhibit limitations in achieving satisfactory topological performance, particularly in terms of preserving connectivity. To address this challenge, we propose a novel deep-learning approach, termed Deep Closing, inspired by the well-established classic closing operation. Deep Closing first leverages an AutoEncoder trained in the Masked Image Modeling (MIM) paradigm, enhanced with digital topology knowledge, to effectively learn the inherent shape prior of tubular structures and indicate potential disconnected regions. Subsequently, a Simple Components Erosion module is employed to generate topology-focused outcomes, which refines the preceding segmentation results, ensuring all the generated regions are topologically significant. To evaluate the efficacy of Deep Closing, we conduct comprehensive experiments on 4 datasets: DRIVE, CHASE DB1, DCA1, and CREMI. The results demonstrate that our approach yields considerable improvements in topological performance compared with existing methods. Furthermore, Deep Closing exhibits the ability to generalize and transfer knowledge from external datasets, showcasing its robustness and adaptability. The code for this paper has been available at: https://github.com/5k5000/DeepClosing.
- 27 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 43 (11) , 3990-4003
Deep Closing: Enhancing Topological Connectivity in Medical Tubular Segmentation
Accurately segmenting tubular structures, such as blood vessels or nerves, holds significant clinical implications across various medical applications. However, existing methods often exhibit limitations in achieving satisfactory topological performance, particularly in terms of preserving connectivity. To address this challenge, we propose a novel deep-learning approach, termed Deep Closing, inspired by the well-established classic closing operation. Deep Closing first leverages an AutoEncoder trained in the Masked Image Modeling (MIM) paradigm, enhanced with digital topology knowledge, to effectively learn the inherent shape prior of tubular structures and indicate potential disconnected regions. Subsequently, a Simple Components Erosion module is employed to generate topology-focused outcomes, which refines the preceding segmentation results, ensuring all the generated regions are topologically significant. To evaluate the efficacy of Deep Closing, we conduct comprehensive experiments on 4 datasets: DRIVE, CHASE DB1, DCA1, and CREMI. The results demonstrate that our approach yields considerable improvements in topological performance compared with existing methods. Furthermore, Deep Closing exhibits the ability to generalize and transfer knowledge from external datasets, showcasing its robustness and adaptability. The code for this paper has been available at: https://github.com/5k5000/DeepClosing.
- 13 October 2021
- Published by Springer Nature
- p. 66-75
Ensemble of Adapters for Transfer Learning Based on Evidence Theory
- 13 October 2021
- Published by Springer Nature
- p. 66-75
Ensemble of Adapters for Transfer Learning Based on Evidence Theory
- 25 February 2008
- Published by Springer Nature
- p. 61-69
A Fast Longest Common Subsequence Algorithm for Biosequences Alignment
- 25 February 2008
- Published by Springer Nature
- p. 61-69
A Fast Longest Common Subsequence Algorithm for Biosequences Alignment
- 1 April 2007
- Published by IOP Publishing in Chinese Physics Letters
- Vol. 24 (4) , 986-989
Feasibility of Non-Collinear TeO 2 Acoustic-Optic Tunable Filters Used in the Optical Communication
- 1 April 2007
- Published by IOP Publishing in Chinese Physics Letters
- Vol. 24 (4) , 986-989
Feasibility of Non-Collinear TeO 2 Acoustic-Optic Tunable Filters Used in the Optical Communication