← Search

Wenlei Liu

2 accepted papers

2023

Learnable Flow Model Conditioned on Graph Representation Memory for Anomaly Detection

ICASSP 2023accepted

Anomaly detection could be applied in a wide range of fields from industrial scene to medical imaging analysis. Although invertible flow models are developed to accomplish unsupervised anomaly detection, they are usually hard to train and have limited capabilities of accurately modeling the distribu…

Cited by 0SourceScholar
2022

DuMLP-Pin: A Dual-MLP-Dot-Product Permutation-Invariant Network for Set Feature Extraction

AAAI 2022technical

Existing permutation-invariant methods can be divided into two categories according to the aggregation scope, i.e. global aggregation and local one. Although the global aggregation methods, e. g., PointNet and Deep Sets, get involved in simpler structures, their performance is poorer than the local…