5 papers
Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers
Renzhen Wang, De cai, Kaiwen Xiao +3
Hierarchical classification aims to sort the object into a hierarchical structure of categories. For example, a bird can be categorized according to a three-level hierarchy of orde…
Semi-Supervised Regression with Heteroscedastic Pseudo-Labels
Xueqing Sun, Renzhen Wang, Quanziang Wang +3
Pseudo-labeling is a commonly used paradigm in semi-supervised learning, yet its application to semi-supervised regression (SSR) remains relatively under-explored. Unlike classific…
Data-Distill-Net: A Data Distillation Approach Tailored for Reply-based Continual Learning
Wenyang Liao, Quanziang Wang, Yichen Wu +2
Replay-based continual learning (CL) methods assume that models trained on a small subset can also effectively minimize the empirical risk of the complete dataset. These methods ma…
Singular Value Fine-tuning for Few-Shot Class-Incremental Learning
Zhiwu Wang, Yichen Wu, Renzhen Wang +4
Class-Incremental Learning (CIL) aims to prevent catastrophic forgetting of previously learned classes while sequentially incorporating new ones. The more challenging Few-shot CIL…
SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning
Yichen Wu, Hongming Piao, Long-Kai Huang +6
Continual Learning (CL) with foundation models has recently emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks…