Related papers: CF-Net: A Cross-Feature Reconstruction Network for…
Deep learning has substantially advanced medical image segmentation, yet achieving robust generalization across diverse imaging modalities and anatomical structures remains a major challenge. A key contributor to this limitation lies in how…
We present a deep neural network-enabled method to accelerate near-field (NF) antenna measurement. We develop a Near-field Super-resolution Network (NFS-Net) to reconstruct significantly undersampled near-field data as high-resolution data,…
Compressing neural networks by quantizing model parameters offers useful trade-off between performance and efficiency. Methods like quantization-aware training and post-training quantization strive to maintain the downstream performance of…
Undersampling k-space data in MRI reduces scan time but pose challenges in image reconstruction. Considerable progress has been made in reconstructing accelerated MRI. However, restoration of high-frequency image details in highly…
Deep learning has enabled realistic face manipulation (i.e., deepfake), which poses significant concerns over the integrity of the media in circulation. Most existing deep learning techniques for deepfake detection can achieve promising…
In this paper, we propose a new deep image compression framework called Complexity and Bitrate Adaptive Network (CBANet), which aims to learn one single network to support variable bitrate coding under different computational complexity…
In wireless communication systems, the asynchronization of the oscillators in the transmitter and the receiver along with the Doppler shift due to relative movement may lead to the presence of carrier frequency offset (CFO) in the received…
Quantizing weights and activations of deep neural networks is essential for deploying them in resource-constrained devices, or cloud platforms for at-scale services. While binarization is a special case of quantization, this extreme case…
Neural network quantization aims to transform high-precision weights and activations of a given neural network into low-precision weights/activations for reduced memory usage and computation, while preserving the performance of the original…
We introduce a data-free quantization method for deep neural networks that does not require fine-tuning or hyperparameter selection. It achieves near-original model performance on common computer vision architectures and tasks. 8-bit…
The detection and estimation of sinusoids is a fundamental signal processing task for many applications related to sensing and communications. While algorithms have been proposed for this setting, quantization is a critical, but often…
Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources. Network quantization is a powerful technique to compress neural networks, allowing for more…
In the practical application of restoring low-resolution gray-scale images, we generally need to run three separate processes of image colorization, super-resolution, and dows-sampling operation for the target device. However, this pipeline…
Mitotic count (MC) is an important histological parameter for cancer diagnosis and grading, but the manual process for obtaining MC from whole-slide histopathological images is very time-consuming and prone to error. Therefore, deep…
Deep complex-valued neural networks (CVNNs) provide a powerful way to leverage complex number operations and representations and have succeeded in several phase-based applications. However, previous networks have not fully explored the…
To realize the promise of ubiquitous embedded deep network inference, it is essential to seek limits of energy and area efficiency. To this end, low-precision networks offer tremendous promise because both energy and area scale down…
Classification of very high resolution (VHR) satellite images has three major challenges: 1) inherent low intra-class and high inter-class spectral similarities, 2) mismatching resolution of available bands, and 3) the need to regularize…
CTR prediction has been widely used in the real world. Many methods model feature interaction to improve their performance. However, most methods only learn a fixed representation for each feature without considering the varying importance…
Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of…
The emergence of ResNet provides a powerful tool for training extremely deep networks. The core idea behind it is to change the learning goals of the network. It no longer learns new features from scratch but learns the difference between…