collaborators

5 papers

cs.CV2025

Meta-Learned Modality-Weighted Knowledge Distillation for Robust Multi-Modal Learning with Missing Data

Hu Wang, Salma Hassan, Yuyuan Liu +12

In multi-modal learning, some modalities are more influential than others, and their absence can have a significant impact on classification/segmentation accuracy. Addressing this…

cs.LG2025

Rethinking Weight-Averaged Model-merging

Hu Wang, Congbo Ma, Ibrahim Almakky +3

Model merging, particularly through weight averaging, has shown surprising effectiveness in saving computations and improving model performance without any additional training. How…

cs.CV2025

ItTakesTwo: Leveraging Peer Representations for Semi-supervised LiDAR Semantic Segmentation

Yuyuan Liu, Yuanhong Chen, Hu Wang +3

The costly and time-consuming annotation process to produce large training sets for modelling semantic LiDAR segmentation methods has motivated the development of semi-supervised l…

cs.CV2025

Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality

Hu Wang, Congbo Ma, Jianpeng Zhang +4

The problem of missing modalities is both critical and non-trivial to be handled in multi-modal models. It is common for multi-modal tasks that certain modalities contribute more c…

cs.CV2024

Human-AI Collaborative Multi-modal Multi-rater Learning for Endometriosis Diagnosis

Hu Wang, David Butler, Yuan Zhang +5

Endometriosis, affecting about 10% of individuals assigned female at birth, is challenging to diagnose and manage. Diagnosis typically involves the identification of various signs…