From the 1 of 6 linked papers with an AI index.
6 papers
SIVA-RL: Sensitivity-Invariance Visual Alignment for Multimodal Reinforcement Learning
Cheng Tang, Junzhi Ning, Min Cen +9
The paper presents SIVA-RL, a framework that uses sample-wise visual interventions to align sensitivity and invariance in multimodal reinforcement learning models, leading to bette…
Incorporating the Refractory Period into Spiking Neural Networks through Spike-Triggered Threshold Dynamics
Yang Li, Xinyi Zeng, Zhe Xue +3
As the third generation of neural networks, spiking neural networks (SNNs) have recently gained widespread attention for their biological plausibility, energy efficiency, and effec…
Adaptive Hardness-driven Augmentation and Alignment Strategies for Multi-Source Domain Adaptations
Yang Yuxiang, Zeng Xinyi, Zeng Pinxian +4
Multi-source Domain Adaptation (MDA) aims to transfer knowledge from multiple labeled source domains to an unlabeled target domain. Nevertheless, traditional methods primarily focu…
BTMuda: A Bi-level Multi-source unsupervised domain adaptation framework for breast cancer diagnosis
Yuxiang Yang, Xinyi Zeng, Pinxian Zeng +4
Deep learning has revolutionized the early detection of breast cancer, resulting in a significant decrease in mortality rates. However, difficulties in obtaining annotations and hu…
S3PET: Semi-supervised Standard-dose PET Image Reconstruction via Dose-aware Token Swap
Jiaqi Cui, Pinxian Zeng, Yuanyuan Xu +3
To acquire high-quality positron emission tomography (PET) images while reducing the radiation tracer dose, numerous efforts have been devoted to reconstructing standard-dose PET (…
MCAD: Multi-modal Conditioned Adversarial Diffusion Model for High-Quality PET Image Reconstruction
Jiaqi Cui, Xinyi Zeng, Pinxian Zeng +4
Radiation hazards associated with standard-dose positron emission tomography (SPET) images remain a concern, whereas the quality of low-dose PET (LPET) images fails to meet clinica…