Zhongyi Sun

Learning Distinctive Margin toward Active Domain Adaptation

Despite plenty of efforts focusing on improving the domain adaptation ability (DA) under unsupervised or few-shot semi-supervised settings, recently the solution of active learning started to...

Combining Past, Present and Future: A Self-Supervised Approach for Class Incremental Learning

Class Incremental Learning (CIL) aims to handle the scenario where data of novel classes occur continuously and sequentially. The model should recognize the sequential novel classes while...

Superpixel-based active learning for the classification of hyperspectral images

A Spark-Based Big Data Platform for Massive Remote Sensing Data Processing

Learning Distinctive Margin toward Active Domain Adaptation

Search for Gravitational Wave Probes - A Self-Supervised Learning for Pulsars Based on Signal Contexts

ProAug: Prototype-Based Augmentation for Long-Tailed Image Classification

SAFA: Sample-Adaptive Feature Augmentation for Long-Tailed Image Classification

A Longitudinal Study of the Evolution of the Central Sulcus' Shape in Preterm Infants Using Manifold Learning

Towards a Foundation Model for Cortical Folding

Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models

Computational Efficiency Active Learning for classification of hyperspectral images

Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models

Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs), where improving performance on unseen tasks often leads to a significant...