Related papers: AdaBM: On-the-Fly Adaptive Bit Mapping for Image S…
Reducing the latency and model size has always been a significant research problem for live Automatic Speech Recognition (ASR) application scenarios. Along this direction, model quantization has become an increasingly popular approach to…
One-step diffusion-based image super-resolution (OSDSR) models are showing increasingly superior performance nowadays. However, although their denoising steps are reduced to one and they can be quantized to 8-bit to reduce the costs…
Quantized low-precision neural networks are very popular because they require less computational resources for inference and can provide high performance, which is vital for real-time and embedded recognition systems. However, their…
Creating 3D semantic reconstructions of environments is fundamental to many applications, especially when related to autonomous agent operation (e.g., goal-oriented navigation or object interaction and manipulation). Commonly, 3D semantic…
Deep convolutional neural networks have significantly improved the peak signal-to-noise ratio of SuperResolution (SR). However, image viewer applications commonly allow users to zoom the images to arbitrary magnification scales, thus far…
Recent attempts at Super-Resolution for medical images used deep learning techniques such as Generative Adversarial Networks (GANs) to achieve perceptually realistic single image Super-Resolution. Yet, they are constrained by their…
Image compression techniques have made remarkable progress when it comes to file size reduction with a tolerable quality reduction; nonetheless, they are facing some challenges when it comes to applying more compression with the same…
This paper presents an adaptive image sampling algorithm based on Deep Learning (DL). The adaptive sampling mask generation network is jointly trained with an image inpainting network. The sampling rate is controlled in the mask generation…
This work demonstrates a hardware-efficient support vector machine (SVM) training algorithm via the alternative direction method of multipliers (ADMM) optimizer. Low-rank approximation is exploited to reduce the dimension of the kernel…
Recently, deep learning-based image compression has made signifcant progresses, and has achieved better ratedistortion (R-D) performance than the latest traditional method, H.266/VVC, in both subjective metric and the more challenging…
Model quantization is widely applied for compressing and accelerating deep neural networks (DNNs). However, conventional Quantization-Aware Training (QAT) focuses on training DNNs with uniform bit-width. The bit-width settings vary across…
Diffusion models have demonstrated remarkable capabilities in image synthesis and related generative tasks. Nevertheless, their practicality for real-world applications is constrained by substantial computational costs and latency issues.…
In point-based sensing systems such as coordinate measuring machines (CMM) and laser ultrasonics where complete sensing is impractical due to the high sensing time and cost, adaptive sensing through a systematic exploration is vital for…
This work proposes a novel shape optimization framework for geometric inverse problems governed by the advection--diffusion equation, based on the coupled complex boundary method (CCBM). Building on recent developments [Afr22, Rab23, Rab25,…
Convolutional neural networks have recently achieved significant breakthroughs in various image classification tasks. However, they are computationally expensive,which can make their feasible mplementation on embedded and low-power devices…
Image super-resolution (SR) techniques have been developing rapidly, benefiting from the invention of deep networks and its successive breakthroughs. However, it is acknowledged that deep learning and deep neural networks are difficult to…
In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable. However, most deep learning methods only achieve high performance in one aspect due to the perception-distortion trade-off, and works that…
Recent work showed neural-network-based approaches to reconstructing images from compressively sensed measurements offer significant improvements in accuracy and signal compression. Such methods can dramatically boost the capability of…
Deep learning based image Super-Resolution (SR) has shown rapid development due to its ability of big data digestion. Generally, deeper and wider networks can extract richer feature maps and generate SR images with remarkable quality.…
Previous methods decompose blind super resolution (SR) problem into two sequential steps: \textit{i}) estimating blur kernel from given low-resolution (LR) image and \textit{ii}) restoring SR image based on estimated kernel. This two-step…