刘夏雷｜南开大学｜学者主页

2026

Towards Understanding Token Evolution in Continual Learning of MLLMs

Xusheng Cao, Yifan Meng, Jiaze Li, Jianzhong Ju, Zhenbo Luo, Jian Luan, Fei Yang, Ming‐Ming Cheng, Xialei Liu

International Journal of Computer Vision

DOI

2026

Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection

Xinbin Yuan, Zhaohui Zheng, Yuxuan Li, Xialei Liu, Li Liu, Xiang Li, Qibin Hou, Ming-Ming Cheng

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2026

See More, Know More: Richer Prior Knowledge for Novel Class Discovery

Zhimao Peng, Enguang Wang, Xialei Liu, Ming‐Ming Cheng

Computational Visual Media

DOI

2026

Sharpness-Aware Dynamic Anchor Selection for Generalized Category Discovery

Zhimao Peng, Enguang Wang, Fei Yang, Xialei Liu, Ming‐Ming Cheng

IEEE Transactions on Multimedia

DOI

2026

Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery

Enguang Wang, Zhimao Peng, Zhengyuan Xie, Haori Lu, Fei Yang, Xialei Liu

IEEE Transactions on Multimedia

DOI

2026

Restoring Forgotten Knowledge in Non-Exemplar Class Incremental Image Classification through Test-Time Semantic Evolution

Haori Lu, Xusheng Cao, Linlan Huang, Enguang Wang, Fei Yang, Xialei Liu

IEEE Transactions on Multimedia

DOI

2026

Task-Agnostic Incremental Vision-Language Object Detection via Prompt Augmentation and Distribution-Aware Fusion

Yonghan Jiang, Zhengyuan Xie, Wenchu Liu, Linlan Huang, Fei Yang, Xialei Liu

Lecture notes in computer science

DOI

2025

Bridging Inter-Task Gap of Continual Self-Supervised Learning With External Data

Haori Lu, Xusheng Cao, Linlan Huang, Enguang Wang, Fei Yang, Xialei Liu

IEEE Transactions on Circuits and Systems for Video Technology

DOI

2025

KAC: Kolmogorov-Arnold Classifier for Continual Learning

Yusong Hu, Zichen Liang, Fei Yang, Qibin Hou, Xialei Liu, Ming‐Ming Cheng

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2025

Class Incremental Learning for Image Classification With Out-of-Distribution Task Identification

Xusheng Cao, Haori Lu, Xialei Liu, Ming‐Ming Cheng

IEEE Transactions on Multimedia

DOI

2025

Enhancing Continual Semantic Segmentation via Uncertainty and Class Balance Re-Weighting

Zichen Liang, Yusong Hu, Fei Yang, Xialei Liu

IEEE Transactions on Image Processing

DOI

2025

Hybrid Re-matching for Continual Learning with Parameter-Efficient Tuning

Weicheng Wang, Guoli Jia, Xialei Liu, Liang Lin, Jufeng Yang

neural information processing systems

DOI

2025

Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning

Xusheng Cao, Haori Lu, Linlan Huang, Fei Yang, Xialei Liu, Ming‐Ming Cheng

neural information processing systems

DOI

2024

基于深度学习的半监督语义分割综述

孙博远，刘夏雷，侯淇彬

《北京交通大学学报》

2024

Predictive Sample Assignment for Semantically Coherent Out-of-Distribution Detection

Zhimao Peng, Enguang Wang, Xialei Liu, Ming‐Ming Cheng

IEEE Transactions on Circuits and Systems for Video Technology

DOI

2024

Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion

Linlan Huang, Xusheng Cao, Haori Lu, Xialei Liu

Lecture notes in computer science

DOI

2024

Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation

Zhengyuan Xie, Haiquan Lu, Jia-wen Xiao, Enguang Wang, Le Zhang, Xialei Liu

Lecture notes in computer science

DOI

2024

$$A^{3}R$$: Vision Language Pre-training by Attentive Alignment and Attentive Reconstruction

Yusong Hu, Yuting Gao, Zihan Xu, Ke Li, Xialei Liu

Lecture notes in computer science

DOI

2024

Let’s Start Over: Retraining with Selective Samples for Generalized Category Discovery

Zhimao Peng, Enguang Wang, Xialei Liu, Ming-Ming Cheng

DOI

2024

Generative Multi-modal Models are Good Class-Incremental Learners

Xusheng Cao, Haori Lu, Linlan Huang, Xialei Liu, Ming‐Ming Cheng

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2024

Fine-Grained Knowledge Selection and Restoration for Non-exemplar Class Incremental Learning

Jiang-Tian Zhai, Xialei Liu, Yu Lu, Ming‐Ming Cheng

Proceedings of the AAAI Conference on Artificial Intelligence

DOI

2024

Modeling Inner- and Cross-Task Contrastive Relations for Continual Image Classification

Yuxuan Luo, Runmin Cong, Xialei Liu, Horace H. S. Ip, Sam Kwong

IEEE Transactions on Multimedia

DOI

2023

Universal Representations: A Unified Look at Multiple Task and Domain Learning

Weihong Li, Xialei Liu, Hakan Bilen

International Journal of Computer Vision

DOI

2023

Lighting Every Darkness in Two Pairs : A Calibration-Free Pipeline for RAW Denoising

Xin Jin, Jia-wen Xiao, Ling-Hao Han, Chunle Guo, Ruixun Zhang, Xialei Liu, Chongyi Li

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2023

Masked Autoencoders are Efficient Class Incremental Learners

Jiang-Tian Zhai, Xialei Liu, Andrew D. Bagdanov, Ke Li, Ming‐Ming Cheng

IEEE/CVF International Conference on Computer Vision (ICCV)

DOI

2023

Sequential interactive image segmentation

Lin Liu Zheng, Zhao Zhang, Ziyue Zhu, Deng-Ping Fan, Xialei Liu

Computational Visual Media

DOI

2023

Endpoints Weight Fusion for Class Incremental Semantic Segmentation

Jia–Wen Xiao, Chang–Bin Zhang, Jiekang Feng, Xialei Liu, Joost van de Weijer, Ming‐Ming Cheng

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2022

Representation Compensation Networks for Continual Semantic Segmentation

Chang–Bin Zhang, Jia-wen Xiao, Xialei Liu, Ying-Cong Chen, Ming‐Ming Cheng

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings

DOI

2022

Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition

Kai Wang, Xialei Liu, Andy Bagdanov, Luis Herranz, Shangling Jui, Joost van de Weijer

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

DOI

2022

Self-Training for Class-Incremental Semantic Segmentation

Lu Yu, Xialei Liu, Joost van de Weijer

IEEE Transactions on Neural Networks and Learning Systems

DOI

2022

Long-Tailed Class Incremental Learning

Xialei Liu, Yusong Hu, Xusheng Cao, Andrew D. Bagdanov, Ke Li, Ming‐Ming Cheng

Lecture notes in computer science

DOI

2021

HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification

Kai Wang, Xialei Liu, Luis Herranz, Joost van de Weijer

British Machine Vision Conference (BMVC)

DOI

2013

采用多重约束的无人机导航KLT视觉跟踪算法

宋琳，程咏梅，刘楠，刘夏雷

《红外与激光工程》

2013

基于加权形状上下文的图匹配方法

宋琳，程咏梅，宋春华，刘夏雷

《激光与红外》

精选作品

期刊论文

Towards Understanding Token Evolution in Continual Learning of MLLMs

Strip R-CNN: Large Strip Convolution for Remote Sensing Object Detection

See More, Know More: Richer Prior Knowledge for Novel Class Discovery

Sharpness-Aware Dynamic Anchor Selection for Generalized Category Discovery

Learning Part Knowledge to Facilitate Category Understanding for Fine-Grained Generalized Category Discovery

Restoring Forgotten Knowledge in Non-Exemplar Class Incremental Image Classification through Test-Time Semantic Evolution

Task-Agnostic Incremental Vision-Language Object Detection via Prompt Augmentation and Distribution-Aware Fusion

Bridging Inter-Task Gap of Continual Self-Supervised Learning With External Data

KAC: Kolmogorov-Arnold Classifier for Continual Learning

Class Incremental Learning for Image Classification With Out-of-Distribution Task Identification

Enhancing Continual Semantic Segmentation via Uncertainty and Class Balance Re-Weighting

Hybrid Re-matching for Continual Learning with Parameter-Efficient Tuning

Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning

基于深度学习的半监督语义分割综述

Predictive Sample Assignment for Semantically Coherent Out-of-Distribution Detection

Class-Incremental Learning with CLIP: Adaptive Representation Adjustment and Parameter Fusion

Early Preparation Pays Off: New Classifier Pre-tuning for Class Incremental Semantic Segmentation

$$A^{3}R$$: Vision Language Pre-training by Attentive Alignment and Attentive Reconstruction

Let’s Start Over: Retraining with Selective Samples for Generalized Category Discovery

Generative Multi-modal Models are Good Class-Incremental Learners

Fine-Grained Knowledge Selection and Restoration for Non-exemplar Class Incremental Learning

Modeling Inner- and Cross-Task Contrastive Relations for Continual Image Classification

Universal Representations: A Unified Look at Multiple Task and Domain Learning

Lighting Every Darkness in Two Pairs : A Calibration-Free Pipeline for RAW Denoising

Masked Autoencoders are Efficient Class Incremental Learners

Sequential interactive image segmentation

Endpoints Weight Fusion for Class Incremental Semantic Segmentation

Representation Compensation Networks for Continual Semantic Segmentation

Incremental Meta-Learning via Episodic Replay Distillation for Few-Shot Image Recognition

Self-Training for Class-Incremental Semantic Segmentation

Long-Tailed Class Incremental Learning

HCV: Hierarchy-Consistency Verification for Incremental Implicitly-Refined Classification

采用多重约束的无人机导航KLT视觉跟踪算法

基于加权形状上下文的图匹配方法

预印本

Weaving Light and Time: Unified Harmonic-Geometric Representation Learning for Dense RGB-Event Parsing

Class Incremental Learning with Pre-trained Vision-Language Models

研究方向