相关论文: Fully Quantized Image Super-Resolution Networks

Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…

Diffusion-based image super-resolution (ISR) has shown strong potential, but it still struggles in real-world scenarios where degradations are unknown and spatially non-uniform, often resulting in lost details or visual artifacts. To…

Quality control (QC) has long been considered essential to guarantee the reliability of neuroimaging studies. It is particularly important for fetal brain MRI, where acquisitions and image processing techniques are less standardized than in…

Low-bit deep neural networks (DNNs) become critical for embedded applications due to their low storage requirement and computing efficiency. However, they suffer much from the non-negligible accuracy drop. This paper proposes the stochastic…

Implicit neural representations have shown potential in various applications. However, accurately reconstructing the image or providing clear details via image super-resolution remains challenging. This paper introduces Quantum Fourier…

Quantum Kernels are projected to provide early-stage usefulness for quantum machine learning. However, highly sophisticated classical models are hard to surpass without losing interpretability, particularly when vast datasets can be…

Quantization-aware training (QAT) schemes have been shown to achieve near-full precision accuracy. They accomplish this by training a quantized model for multiple epochs. This is computationally expensive, mainly because of the full…

Face Super-Resolution (SR) is a domain-specific super-resolution problem. The specific facial prior knowledge could be leveraged for better super-resolving face images. We present a novel deep end-to-end trainable Face Super-Resolution…

Model quantization is challenging due to many tedious hyper-parameters such as precision (bitwidth), dynamic range (minimum and maximum discrete values) and stepsize (interval between discrete values). Unlike prior arts that carefully tune…

This work introduces a novel quantum algorithm for gradient-based edge detection that operates entirely within the quantum circuit model. Grayscale images are encoded using the Novel Enhanced Quantum Representation (NEQR), allowing exact…

With unprecedented rapid development, deep neural networks (DNNs) have deeply influenced almost all fields. However, their heavy computation costs and model sizes are usually unacceptable in real-world deployment. Model quantization, an…

Visual tokenizers are fundamental to image generation. They convert visual data into discrete tokens, enabling transformer-based models to excel at image generation. Despite their success, VQ-based tokenizers like VQGAN face significant…

Quantization has been proven to be a vital method for improving the inference efficiency of deep neural networks (DNNs). However, it is still challenging to strike a good balance between accuracy and efficiency while quantizing DNN weights…

The recent release of the third generation partnership project, Release 17, calls for sub-meter cellular positioning accuracy with reduced latency in calculation. To provide such high accuracy on a worldwide scale, leveraging the received…

For efficient neural network inference, it is desirable to achieve state-of-the-art accuracy with the simplest networks requiring the least computation, memory, and power. Quantizing networks to lower precision is a powerful technique for…

This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained…

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Among existing QAT methods, one major drawback is that the…

Methods based on convolutional neural network (CNN) have demonstrated tremendous improvements on single image super-resolution. However, the previous methods mainly restore images from one single area in the low resolution (LR) input, which…

Based on the model's resilience to computational noise, model quantization is important for compressing models and improving computing speed. Existing quantization techniques rely heavily on experience and "fine-tuning" skills. In the…

Deep learning-based single-image super-resolution (SISR) technology focuses on enhancing low-resolution (LR) images into high-resolution (HR) ones. Although significant progress has been made, challenges remain in computational complexity…