Changzhe Jiao — accepted AI-conference papers

2026

TIM++: Transductive Information Maximization for Few-Shot CLIP

Yingping Li, Yutong Zou, Yunshi Huang, Changzhe Jiao, Xinlin Wang, Shen Peng +2

AAAI 2026technical

Transductive Information Maximization (TIM) is a leading transductive few-shot learning method that maximizes the mutual information between query features and their predicted labels, while incorporating supervision from the support set. However, its potential remains underexplored, primarily due to

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection

Ying Yang, De Cheng, Chaowei Fang, Yubiao Wang, Changzhe Jiao, Lechao Cheng +2

NeurIPS 2024poster

Unsupervised out-of-distribution (OOD) detection aims to identify out-of-domain data by learning only from unlabeled In-Distribution (ID) training samples, which is crucial for developing a safe real-world machine learning system. Current reconstruction-based method provides a good alternative appro…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗