5 papers
Diverse Normal Prototypes-Guided Contrastive Reconstruction for Medical Anomaly Detection
Luhu Li, Bin Liu, Bowen Lin +3
Anomaly detection in medical images is challenging due to limited annotations and the domain gap. Existing reconstruction-based methods often rely on frozen pre-trained encoders, r…
DM3D: Dynamic Mamba via Offset-Guided Feature Resampling for Point Cloud Understanding
Bin Liu, Chunyang Wang, Xuelian Liu +2
State Space Models (SSMs) model long token sequences of point cloud with linear complexity, but require an unordered point cloud to be serialized. Existing methods mainly address t…
SM3D: Mitigating Spectral Bias and Semantic Dilution in Point Cloud State Space Models
Bin Liu, Chunyang Wang, Xuelian Liu
Point clouds are a fundamental 3D data representation that underpins various computer vision tasks. Recently, Mamba has demonstrated strong potential for 3D point cloud understandi…
Adaptive Dual-Weighted Gravitational Point Cloud Denoising Method
Ge Zhang, Chunyang Wang, Bin Liu +1
High-quality point cloud data is a critical foundation for tasks such as autonomous driving and 3D reconstruction. However, LiDAR-based point cloud acquisition is often affected by…
Post-Training Quantization for 3D Medical Image Segmentation: A Practical Study on Real Inference Engines
Chongyu Qu, Ritchie Zhao, Ye Yu +6
Quantizing deep neural networks ,reducing the precision (bit-width) of their computations, can remarkably decrease memory usage and accelerate processing, making these models more…