Junru Cheng — accepted AI-conference papers

2025

COREMIL: Contextual Position Encoding-based Retrievable Multiple Instance Learning for Slide-level Classification

Bingchen Li, Qiming He, Junru Cheng, Tian Guan, Yonghong He, Guangde Zhou

ICASSP 2025accepted

Multiple Instance Learning (MIL) consists of two stages: feature encoding of instances and feature fusion of instances. This paper identifies two issues in the feature fusion stage of MIL when applied to pathological image classification, which creates performance bottlenecks. First, previous MIL me…

Cited by 0 Source ↗Scholar ↗

2024

HIQ: One-Shot Network Quantization for Histopathological Image Classification

Xinrui Chen, Renao Yan, Yizhi Wang, Jiawen Li, Junru Cheng, Tian Guan +1

ICASSP 2024accepted

To deploy neural networks on clinical edge devices, quantization is the most commonly used method to compress the models, which requires a calibration set of hundreds of real images. However, due to privacy concerns, the scarcity of private histopathological images hinders the application of quantiz…

Cited by 0 Source ↗Scholar ↗