Related papers: Pruned Convolutional Attention Network Based Wideb…

Filter pruning of a CNN is typically achieved by applying discrete masks on the CNN's filter weights or activation maps, post-training. Here, we present a new filter-importance-scoring concept named pruning by active attention manipulation…

Weakly-supervised segmentation (WSS) has emerged as a solution to mitigate the conflict between annotation cost and model performance by adopting sparse annotation formats (e.g., point, scribble, block, etc.). Typical approaches attempt to…

As a paradigm to recover the sparse signal from a small set of linear measurements, compressed sensing (CS) has stimulated a great deal of interest in recent years. In order to apply the CS techniques to wireless communication systems,…

A novel distributed compressed wideband sensing scheme for Cognitive Radio Sensor Networks (CRSN) is proposed in this paper. Taking advantage of the distributive nature of CRSN, the proposed scheme deploys only one single narrowband sampler…

Structured channel pruning has been shown to significantly accelerate inference time for convolution neural networks (CNNs) on modern hardware, with a relatively minor loss of network accuracy. Recent works permanently zero these channels…

In computer vision, convolutional networks (CNNs) often adopts pooling to enlarge receptive field which has the advantage of low computational complexity. However, pooling can cause information loss and thus is detrimental to further…

Speech dereverberation is an important stage in many speech technology applications. Recent work in this area has been dominated by deep neural network models. Temporal convolutional networks (TCNs) are deep learning models that have been…

Graph convolution networks (GCNs) are currently mainstream in learning with irregular data. These models rely on message passing and attention mechanisms that capture context and node-to-node relationships. With multi-head attention, GCNs…

To improve the execution speed and efficiency of neural networks in embedded systems, it is crucial to decrease the model size and computational complexity. In addition to conventional compression techniques, e.g., weight pruning and…

Wireless sensor networks (WSN) acts as the backbone of Internet of Things (IoT) technology. In WSN, field sensing and fusion are the most commonly seen problems, which involve collecting and processing of a huge volume of spatial samples in…

While self-supervised speech representation learning (SSL) models serve a variety of downstream tasks, these models have been observed to overfit to the domain from which the unlabelled data originates. To alleviate this issue, we propose…

A resource-adaptive supernet adjusts its subnets for inference to fit the dynamically available resources. In this paper, we propose prioritized subnet sampling to train a resource-adaptive supernet, termed PSS-Net. We maintain multiple…

Accurate and efficient channel state information (CSI) feedback is crucial for unlocking the substantial spectral efficiency gains of extremely large-scale MIMO (XL-MIMO) systems in future 6G networks. However, the combination of near-field…

Large, pre-trained models are problematic to use in resource constrained applications. Fortunately, task-aware structured pruning methods offer a solution. These approaches reduce model size by dropping structural units like layers and…

Recently, multi-task spoken language understanding (SLU) models have emerged, designed to address various speech processing tasks. However, these models often rely on a large number of parameters. Also, they often encounter difficulties in…

Weight pruning has been widely acknowledged as a straightforward and effective method to eliminate redundancy in Deep Neural Networks (DNN), thereby achieving acceleration on various platforms. However, most of the pruning techniques are…

Compressive sensing (CS), aiming to reconstruct an image/signal from a small set of random measurements has attracted considerable attentions in recent years. Due to the high dimensionality of images, previous CS methods mainly work on…

Wireless power transfer (WPT) is expected to be a technology reshaping the landscape of low-power applications such as the Internet of Things, machine-to-machine communications and radio frequency identification networks. Although there has…

Spectrum sensing is an essential enabling functionality for cognitive radio networks to detect spectrum holes and opportunistically use the under-utilized frequency bands without causing harmful interference to legacy networks. This paper…

Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have millions of parameters represented as floats which make them…