相关论文: Real-time Denoising and Dereverberation with Tiny …

Existing self-supervised pre-trained speech models have offered an effective way to leverage massive unannotated corpora to build good automatic speech recognition (ASR). However, many current models are trained on a clean corpus from a…

ResNets (or Residual Networks) are one of the most commonly used models for image classification tasks. In this project, we design and train a modified ResNet model for CIFAR-10 image classification. In particular, we aimed at maximizing…

A two-stage lightweight online dereverberation algorithm for hearing devices is presented in this paper. The approach combines a multi-channel multi-frame linear filter with a single-channel single-frame post-filter. Both components rely on…

Over the past few decades, underwater image enhancement has attracted increasing amount of research effort due to its significance in underwater robotics and ocean engineering. Research has evolved from implementing physics-based solutions…

Despite the remarkable performance, modern deep neural networks are inevitably accompanied by a significant amount of computational cost for learning and deployment, which may be incompatible with their usage on edge devices. Recent efforts…

In recent years, Denoising Diffusion Models have demonstrated remarkable success in generating semantically valuable pixel-wise representations for image generative modeling. In this study, we propose a novel end-to-end framework, called…

Although deep learning based models for underwater image enhancement have achieved good performance, they face limitations in both lightweight and effectiveness, which prevents their deployment and application on resource-constrained…

Deep neural networks (DNNs) have become a widely deployed model for numerous machine learning applications. However, their fixed architecture, substantial training cost, and significant model redundancy make it difficult to efficiently…

DTMM is a library designed for efficient deployment and execution of machine learning models on weak IoT devices such as microcontroller units (MCUs). The motivation for designing DTMM comes from the emerging field of tiny machine learning…

The real-time segmentation of surgical instruments plays a crucial role in robot-assisted surgery. However, it is still a challenging task to implement deep learning models to do real-time segmentation for surgical instruments due to their…

State-of-the-art segmentation methods rely on very deep networks that are not always easy to train without very large training datasets and tend to be relatively slow to run on standard GPUs. In this paper, we introduce a novel recurrent…

Noise suppression and echo cancellation are critical in speech enhancement and essential for smart devices and real-time communication. Deployed in voice processing front-ends and edge devices, these algorithms must ensure efficient…

In this paper, we address the design of lightweight deep learning-based edge detection. The deep learning technology offers a significant improvement on the edge detection accuracy. However, typical neural network designs have very high…

The resource requirements of deep neural networks (DNNs) pose significant challenges to their deployment on edge devices. Common approaches to address this issue are pruning and mixed-precision quantization, which lead to latency and memory…

For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is deep (to ensure performance) and yet thin (to improve…

In this paper, we propose a novel Convolutional Neural Network (CNN) architecture for learning multi-scale feature representations with good tradeoffs between speed and accuracy. This is achieved by using a multi-branch network, which has…

Real-world image super-resolution (Real-ISR) focuses on recovering high-quality images from low-resolution inputs that suffer from complex degradations like noise, blur, and compression. Recently, diffusion models (DMs) have shown great…

Delineation approaches provide significant benefits to various domains, including agriculture, environmental and natural disasters monitoring. Most of the work in the literature utilize traditional segmentation methods that require a large…

The deployment of deep neural networks on resource-constrained devices necessitates effective model com- pression strategies that judiciously balance the reduction of model size with the preservation of performance. This study introduces a…

While deep-learning-based image restoration has achieved unprecedented fidelity, deployment on mobile Neural Processing Units (NPUs) remains bottlenecked by operator incompatibility and memory-access overhead. We propose an NPU-aware…