Wangwang Jia — accepted AI-conference papers

2026

Geometry-driven OOD Detectors Are Class-Incremental Learners

Wangwang Jia, Zijian Gao, Tianjiao Wan, Yuan Cao, Yong Dou, Kele Xu

CVPR 2026

Class-Incremental Learning (CIL) seeks to acquire new classes over time without erasing prior knowledge. While recent methods leverage pre-trained models (PTMs) to curb forgetting, they largely optimize the feature extractor and overlook the crucial classification head. In this work, we advance a si

Cited by 0 Source ↗code ↗Scholar ↗

2025

Knowledge Memorization and Rumination for Pre-trained Model-based Class-Incremental Learning

Zijian Gao, Wangwang Jia, Xingxing Zhang, Dulan Zhou, Kele Xu, Feng Dawei +3

CVPR 2025poster

Class-Incremental Learning (CIL) enables models to continuously learn new classes while mitigating catastrophic forgetting. Recently, Pre-Trained Models (PTMs) have greatly enhanced CIL performance, even when fine-tuning is limited to the first task. This advantage is particularly beneficial for CIL…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗