Xialei Liu

22

Papers

67

Total Citations

Papers (22)

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

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

Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

Learning Metrics From Teachers: Compact Networks for Image Embedding

Semantic Drift Compensation for Class-Incremental Learning

Representation Compensation Networks for Continual Semantic Segmentation

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

Learning Multiple Dense Prediction Tasks From Partially Annotated Data

Endpoints Weight Fusion for Class Incremental Semantic Segmentation

RankIQA: Learning From Rankings for No-Reference Image Quality Assessment

Universal Representation Learning From Multiple Domains for Few-Shot Classification

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

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

Masked Autoencoders are Efficient Class Incremental Learners

Long-Tailed Class Incremental Learning

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

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

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

Generative Multi-modal Models are Good Class Incremental Learners

Memory Replay GANs: Learning to Generate New Categories without Forgetting