Related papers: Real-time Denoising and Dereverberation with Tiny …

Artificial neural network pruning is a method in which artificial neural network sizes can be reduced while attempting to preserve the predicting capabilities of the network. This is done to make the model smaller or faster during inference…

Robustness is essential for deep neural networks, especially in security-sensitive applications. To this end, randomized smoothing provides theoretical guarantees for certifying robustness against adversarial perturbations. Recently,…

The inference of Neural Networks is usually restricted by the resources (e.g., computing power, memory, bandwidth) on edge devices. In addition to improving the hardware design and deploying efficient models, it is possible to aggregate the…

In this work, we propose small footprint Convolutional Recurrent Neural Network models applied to the problem of wakeword detection and augment them with scaled dot product attention. We find that false accepts compared to Convolutional…

Large-scale models pre-trained on large-scale datasets have profoundly advanced the development of deep learning. However, the state-of-the-art models for medical image segmentation are still small-scale, with their parameters only in the…

Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices. We propose the low-rank transformer (LRT), a memory-efficient and fast neural…

This paper introduces an innovative method for reducing the computational complexity of deep neural networks in real-time speech enhancement on resource-constrained devices. The proposed approach utilizes a two-stage processing framework,…

With the continuous development of neural networks for computer vision tasks, more and more network architectures have achieved outstanding success. As one of the most advanced neural network architectures, DenseNet shortcuts all feature…

For the difficulty and large computational complexity of modeling more frequency bands, full-band speech enhancement based on deep neural networks is still challenging. Previous studies usually adopt compressed full-band speech features in…

Speech dereverberation is often an important requirement in robust speech processing tasks. Supervised deep learning (DL) models give state-of-the-art performance for single-channel speech dereverberation. Temporal convolutional networks…

When designing fully-convolutional neural network, there is a trade-off between receptive field size, number of parameters and spatial resolution of features in deeper layers of the network. In this work we present a novel network design…

In order to save the memory, we propose a miniaturization method for neural network to reduce the parameter quantity existed in remote sensing (RS) image semantic segmentation model. The compact convolution optimization method is first used…

In the current salient object detection network, the most popular method is using U-shape structure. However, the massive number of parameters leads to more consumption of computing and storage resources which are not feasible to deploy on…

Most recent studies on deep learning based speech enhancement (SE) focused on improving denoising performance. However, successful SE applications require striking a desirable balance between denoising performance and computational cost in…

We present QuickNet, a fast and accurate network architecture that is both faster and significantly more accurate than other fast deep architectures like SqueezeNet. Furthermore, it uses less parameters than previous networks, making it…

Recent works have successfully demonstrated that sparse deep reinforcement learning agents can be competitive against their dense counterparts. This opens up opportunities for reinforcement learning applications in fields where inference…

Over parameterization is a common technique in deep learning to help models learn and generalize sufficiently to the given task; nonetheless, this often leads to enormous network structures and consumes considerable computing resources…

Deep-learning recently show great success across disciplines yet conventionally require time-consuming computer processing or bulky-sized diffractive elements. Here we theoretically propose and experimentally demonstrate a purely-passive…

Transfer learning (TL) for medical image segmentation helps deep learning models achieve more accurate performances when there are scarce medical images. This study focuses on completing segmentation of the ribs from lung ultrasound images…

Neural networks are powering the deployment of embedded devices and Internet of Things. Applications range from personal assistants to critical ones such as self-driving cars. It has been shown recently that models obtained from neural nets…