Publications (29)
Meta Feature Modulator for Long-tailed Recognition
Renzhen Wang, Kaiqin Hu, Yanwen Zhu +3
Deep neural networks often degrade significantly when training data suffer from class imbalance problems. Existing approaches, e.g., re-sampling and re-weighting, commonly address…
DAC-MR: Data Augmentation Consistency Based Meta-Regularization for Meta-Learning
Jun Shu, Xiang Yuan, Deyu Meng +1
Meta learning recently has been heavily researched and helped advance the contemporary machine learning. However, achieving well-performing meta-learning model requires a large amo…
Small Sample Learning in Big Data Era
Jun Shu, Zongben Xu, Deyu Meng
As a promising area in artificial intelligence, a new learning paradigm, called Small Sample Learning (SSL), has been attracting prominent research attention in the recent years. I…
Fractional phase slips across the charge-density-wave domain walls in 1-T TiSe2
Haotian Zhang, Zihao Song, Zhongchen Xu +9
The microscopic origin of the charge density wave (CDW) in 1\textit{T}-TiSe remains controversial, with competing scenarios based on phonon-driven lattice instability and elect…
Diagnosing Batch Normalization in Class Incremental Learning
Minghao Zhou, Quanziang Wang, Jun Shu +2
Extensive researches have applied deep neural networks (DNNs) in class incremental learning (Class-IL). As building blocks of DNNs, batch normalization (BN) standardizes intermedia…
Harnessing the Potential of Optimizing Data Mixtures via Bayesian Domain Reweighting
Xiang Yuan, Kaiqing Lei, Zhenyu Jin +3
The paper proposes a Bayesian method that learns optimal domain weights for multi‑domain pre‑training of large language models by inferring a Dirichlet distribution with Gamma prio…