Xialei Liu

papers

1,049

total citations

papers (18)

Universal Representation Learning From Multiple Domains for Few-Shot Classification

ICCV 2021arXiv

109

citations

Long-Tailed Class Incremental Learning

ECCV 2022arXiv

citations

Learning Multiple Dense Prediction Tasks From Partially Annotated Data

CVPR 2022arXiv

citations

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

ICCV 2023arXiv

citations

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

ECCV 2024arXiv

citations

Generative Multi-modal Models are Good Class Incremental Learners

CVPR 2024arXiv

citations

Masked Autoencoders are Efficient Class Incremental Learners

ICCV 2023arXiv

citations

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery

CVPR 2025arXiv

citations

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

AAAI 2024arXiv

citations

Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning

CVPR 2024arXiv

citations

KAC: Kolmogorov-Arnold Classifier for Continual Learning

CVPR 2025arXiv

citations

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

ICCV 2023arXiv

citations

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

NEURIPS 2025arXiv

citations

Endpoints Weight Fusion for Class Incremental Semantic Segmentation

CVPR 2023

citations

Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning

ICCV 2025arXiv

citations

Xialei Liu

papers (18)

Semantic Drift Compensation for Class-Incremental Learning

Cross-Domain Few-Shot Learning With Task-Specific Adapters

Representation Compensation Networks for Continual Semantic Segmentation

Universal Representation Learning From Multiple Domains for Few-Shot Classification

Long-Tailed Class Incremental Learning

Learning Multiple Dense Prediction Tasks From Partially Annotated Data

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

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

Generative Multi-modal Models are Good Class Incremental Learners

Masked Autoencoders are Efficient Class Incremental Learners

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery

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

Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning

KAC: Kolmogorov-Arnold Classifier for Continual Learning

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

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

Endpoints Weight Fusion for Class Incremental Semantic Segmentation

Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning

papers (18)

Semantic Drift Compensation for Class-Incremental Learning

Cross-Domain Few-Shot Learning With Task-Specific Adapters

Representation Compensation Networks for Continual Semantic Segmentation

Universal Representation Learning From Multiple Domains for Few-Shot Classification

Long-Tailed Class Incremental Learning

Learning Multiple Dense Prediction Tasks From Partially Annotated Data

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

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

Generative Multi-modal Models are Good Class Incremental Learners

Masked Autoencoders are Efficient Class Incremental Learners

GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery

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

Task-Adaptive Saliency Guidance for Exemplar-free Class Incremental Learning

KAC: Kolmogorov-Arnold Classifier for Continual Learning

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

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

Endpoints Weight Fusion for Class Incremental Semantic Segmentation

Mind the Gap: Preserving and Compensating for the Modality Gap in CLIP-Based Continual Learning