ResNet Structure Simplification with the Convolutional Kernel Redundancy Measure

no code implementations • 1 Dec 2022 • Hongzhi Zhu, Robert Rohling, Septimiu Salcudean

Deep learning, especially convolutional neural networks, has triggered accelerated advancements in computer vision, bringing changes into our daily practice.

Image Classification

Semi-supervised MIMO Detection Using Cycle-consistent Generative Adversarial Network

no code implementations • 8 Jun 2022 • Hongzhi Zhu, Yongliang Guo, Wei Xu, Xiaohu You

In this paper, a new semi-supervised deep multiple-input multiple-output (MIMO) detection approach using a cycle-consistent generative adversarial network (CycleGAN) is proposed for communication systems without any prior knowledge of underlying channel distributions.

Generative Adversarial Network

Multi-task UNet: Jointly Boosting Saliency Prediction and Disease Classification on Chest X-ray Images

1 code implementation • 15 Feb 2022 • Hongzhi Zhu, Robert Rohling, Septimiu Salcudean

To support the use of visual attention, this paper describes a novel deep learning model for visual saliency prediction on chest X-ray (CXR) images.

Image Classification Multi-Task Learning +1

Gaze-Guided Class Activation Mapping: Leveraging Human Attention for Network Attention in Chest X-rays Classification

no code implementations • 15 Feb 2022 • Hongzhi Zhu, Septimiu Salcudean, Robert Rohling

However, no previous research has combined the network attention and human attention.