Federated Learning (FL) enables multiple clients to collaboratively lear...
While multi-modal learning has been widely used for MRI reconstruction, ...
Brain-inspired spiking neural networks (SNNs) replace the multiply-accum...
Deep learning models have shown promising performance in the field of
di...
Federated learning (FL), as an effective decentralized distributed learn...
Medical image segmentation (MIS) is essential for supporting disease
dia...
Focusing on the complicated pathological features, such as blurred
bound...
Spiking neural networks (SNN) are a viable alternative to conventional
a...
Spiking neural networks (SNNs) recently gained momentum due to their
low...
In-memory deep learning computes neural network models where they are st...
Compiler frameworks are crucial for the widespread use of FPGA-based dee...
Overparametrized Deep Neural Networks (DNNs) often achieve astounding
pe...
Deep neural networks (DNNs) trained on one set of medical images often
e...
Convolutional neural networks may perform poorly when the test and train...
Medical image segmentation is important for computer-aided diagnosis. Go...
Edge devices demand low energy consumption, cost and small form factor. ...
Countries across the globe have been pushing strict regulations on the
p...
Along with the extensive applications of CNN models for classification, ...
Convolutional Neural Networks (CNNs) are known to be brittle under vario...
This paper studies privacy-preserving weighted federated learning within...
Deep learning for medical image classification faces three major challen...
Deep Neural Networks (DNN) have been successful in en- hancing noisy spe...
Most existing learning to hash methods assume that there are sufficient ...