Related papers: Edge-Efficient Image Restoration: Transformer Dist…

Deploying deep neural networks on mobile devices is a challenging task. Current model compression methods such as matrix decomposition effectively reduce the deployed model size, but still cannot satisfy real-time processing requirement.…

The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for…

Image retrieval is crucial in robotics and computer vision, with downstream applications in robot place recognition and vision-based product recommendations. Modern retrieval systems face two key challenges: scalability and efficiency.…

In recent years, numerous real-time stereo matching methods have been introduced, but they often lack accuracy. These methods attempt to improve accuracy by introducing new modules or integrating traditional methods. However, the…

Our objective is language-based search of large-scale image and video datasets. For this task, the approach that consists of independently mapping text and vision to a joint embedding space, a.k.a. dual encoders, is attractive as retrieval…

Edge inference for large language models (LLM) offers secure, low-latency, and cost-effective inference solutions. We emphasize that an edge accelerator should achieve high area efficiency and minimize external memory access (EMA) during…

Ultra-High-Definition (UHD) image restoration is trapped in a scalability crisis: existing models, bound to pixel-wise operations, demand unsustainable computation. While state space models (SSMs) like Mamba promise linear complexity, their…

We present a simple but novel hybrid approach to hyperspectral data cube reconstruction from computed tomography imaging spectrometry (CTIS) images that sequentially combines neural networks and the iterative Expectation Maximization (EM)…

Recently, the state space model (SSM) represented by Mamba has shown remarkable performance in long-term sequence modeling tasks, including speech enhancement. However, due to substantial differences in sub-band features, applying the same…

We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module, efficient spatial pyramid (ESP), which is…

Sequence modeling plays a vital role across various domains, with recurrent neural networks being historically the predominant method of performing these tasks. However, the emergence of transformers has altered this paradigm due to their…

The advent of Transformer and Mamba-based architectures has significantly advanced 3D medical image segmentation by enabling global contextual modeling, a capability traditionally limited in Convolutional Neural Networks (CNNs). However,…

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…

This paper introduces VMatcher, a hybrid Mamba-Transformer network for semi-dense feature matching between image pairs. Learning-based feature matching methods, whether detector-based or detector-free, achieve state-of-the-art performance…

Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo matching models that deliver high accuracy while operating in real-time continues to be a major challenge in…

Deep learning-based speech enhancement (SE) methods often face significant computational challenges when needing to meet low-latency requirements because of the increased number of frames to be processed. This paper introduces the SlowFast…

Magnetic resonance imaging (MRI) is an important non-invasive clinical tool that can produce high-resolution and reproducible images. However, a long scanning time is required for high-quality MR images, which leads to exhaustion and…

Mining machinery operating in variable environments faces high wear and unpredictable stress, challenging Predictive Maintenance (PdM). This paper introduces the Edge Sensor Network for Predictive Maintenance (ESN-PdM), a hierarchical…

Deep learning-based image compression has made great progresses recently. However, many leading schemes use serial context-adaptive entropy model to improve the rate-distortion (R-D) performance, which is very slow. In addition, the…

Achieving optimal semantic segmentation with frame-based vision sensors poses significant challenges for real-time systems like UAVs and self-driving cars, which require rapid and precise processing. Traditional frame-based methods often…