Related papers: ImageHD: Energy-Efficient On-Device Continual Lear…

This paper introduces FSL-HDnn, an energy-efficient accelerator that implements the end-to-end pipeline of feature extraction, classification, and on-chip few-shot learning (FSL) through gradient-free learning techniques in a 40 nm CMOS…

Convolutional neural networks (CNNs) demand huge DRAM bandwidth for computational imaging tasks, and block-based processing has recently been applied to greatly reduce the bandwidth. However, the induced additional computation for feature…

The recursive quad-tree partitioning in High Efficiency Video Coding (HEVC) incurs considerable computational overhead, with exhaustive rate-distortion optimization for CTU partition prediction consuming the dominant share of encoding time.…

Recently, deep learning-based computer-generated holography (CGH) has demonstrated tremendous potential in three-dimensional (3D) displays and yielded impressive display quality. However, most existing deep learning-based CGH techniques can…

Achieving high-quality High Dynamic Range (HDR) imaging on resource-constrained edge devices is a critical challenge in computer vision, as its performance directly impacts downstream tasks such as intelligent surveillance and autonomous…

Deep learning based methods, such as Convolution Neural Network (CNN), have demonstrated their efficiency in hyperspectral image (HSI) classification. These methods can automatically learn spectral-spatial discriminative features within…

Edge computing allows more computing tasks to take place on the decentralized nodes at the edge of networks. Today many delay sensitive, mission-critical applications can leverage these edge devices to reduce the time delay or even to…

Hyperdimensional computing (HDC) is an emerging computational framework inspired by the brain that operates on vectors with thousands of dimensions to emulate cognition. Unlike conventional computational frameworks that operate on numbers,…

To enhance image compression performance, recent deep neural network-based research can be divided into three categories: a learnable codec, a postprocessing network, and a compact representation network. The learnable codec has been…

The accuracy of deep convolutional neural networks (CNNs) generally improves when fueled with high resolution images. However, this often comes at a high computational cost and high memory footprint. Inspired by the fact that not all…

Considering efficiency, ultra-high-definition (UHD) low-light image restoration is extremely challenging. Existing methods based on Transformer architectures or high-dimensional complex convolutional neural networks often suffer from the…

Image and video descriptors are an omnipresent tool in computer vision and its application fields like mobile robotics. Many hand-crafted and in particular learned image descriptors are numerical vectors with a potentially (very) large…

Deep learning has revolutionized medical image analysis, playing a vital role in modern clinical applications. However, the deployment of large-scale models in real-world clinical settings remains challenging due to high computational…

Continual Learning (CL) aims to sequentially train models on streams of incoming data that vary in distribution by preserving previous knowledge while adapting to new data. Current CL literature focuses on restricted access to previously…

In this paper, we propose a novel quadratic optimized model based on the deep convolutional neural network (QODCNN) for full-reference and no-reference screen content image (SCI) quality assessment. Unlike traditional CNN methods taking all…

Multimodal Large Language Models (MLLMs) have experienced significant advancements recently. Nevertheless, challenges persist in the accurate recognition and comprehension of intricate details within high-resolution images. Despite being…

Change detection is the process of identifying pixelwise differences in bitemporal co-registered images. It is of great significance to Earth observations. Recently, with the emergence of deep learning (DL), the power and feasibility of…

Hyperdimensional Computing (HDC), a technique inspired by cognitive models of computation, has been proposed as an efficient and robust alternative basis for machine learning. HDC programs are often manually written in low-level and target…

Image analysis in the euclidean space through linear hyperspaces is well studied. However, in the quest for more effective image representations, we turn to hyperbolic manifolds. They provide a compelling alternative to capture complex…

Federated Learning (FL) is a distributed learning paradigm that empowers edge devices to collaboratively learn a global model leveraging local data. Simulating FL on GPU is essential to expedite FL algorithm prototyping and evaluations.…