Related papers: A Multi-Stage Optimization Framework for Deploying…

Reconstructing missing details from degraded low-quality inputs poses a significant challenge. Recent progress in image restoration has demonstrated the efficacy of learning large models capable of addressing various degradations…

Learned image compression (LIC) methods have recently outperformed traditional codecs such as VVC in rate-distortion performance. However, their large models and high computational costs have limited their practical adoption. In this paper,…

Parameter quantization for Large Language Models (LLMs) has attracted increasing attentions recently in reducing memory costs and improving computational efficiency. Early approaches have been widely adopted. However, the existing methods…

In recent years, deep learning-based image compression, particularly through generative models, has emerged as a pivotal area of research. Despite significant advancements, challenges such as diminished sharpness and quality in…

Portrait Fidelity Generation is a prominent research area in generative models.Current methods face challenges in generating full-body images with low-resolution faces, especially in multi-ID photo phenomenon.To tackle these issues, we…

Deep neural networks with lower precision weights and operations at inference time have advantages in terms of the cost of memory space and accelerator power. The main challenge associated with the quantization algorithm is maintaining…

We proposed a novel dense line spectrum super-resolution algorithm, the DMRA, that leverages dynamical multi-resolution of atoms technique to address the limitation of traditional compressed sensing methods when handling dense point-source…

Recent advancements in neural network quantisation have yielded remarkable outcomes, with three-bit networks reaching state-of-the-art full-precision accuracy in complex tasks. These achievements present valuable opportunities for…

Deeply learned representations have achieved superior image retrieval performance in a retrieve-then-rerank manner. Recent state-of-the-art single stage model, which heuristically fuses local and global features, achieves promising…

Graph unlearning remains a critical technique for supporting privacy-preserving and sustainable multimodal graph learning. However, we observe that existing unlearning strategies tend to apply uniform parameter selection and editing across…

In modern display technology and visualization tools, downscaling images is one of the most important activities. This procedure aims to maintain both visual authenticity and structural integrity while reducing the dimensions of an image at…

Deep neural networks have achieved state-of-the-art results in a wide range of applications, from natural language processing and computer vision to speech recognition. However, as tasks become increasingly complex, model sizes continue to…

Neural networks with sub-microsecond inference latency are required by many critical applications. Targeting such applications deployed on FPGAs, we present High Granularity Quantization (HGQ), a quantization-aware training framework that…

The application of the context-adaptive entropy model significantly improves the rate-distortion (R-D) performance, in which hyperpriors and autoregressive models are jointly utilized to effectively capture the spatial redundancy of the…

This work integrates StyleGAN, DragGAN and Principal Component Analysis (PCA) to enhance the latent space efficiency and controllability of GAN-generated images. Style-GAN provides a structured latent space, DragGAN enables intuitive image…

Training Deep Neural Networks (DNNs) can be computationally demanding, particularly when dealing with large models. Recent work has aimed to mitigate this computational challenge by introducing 8-bit floating-point (FP8) formats for…

Deep Neural Networks (DNNs) are inherently computation-intensive and also power-hungry. Hardware accelerators such as Field Programmable Gate Arrays (FPGAs) are a promising solution that can satisfy these requirements for both embedded and…

Low precision data representation is important to reduce storage size and memory access for convolutional neural networks (CNNs). Yet, existing methods have two major limitations: (1) requiring re-training to maintain accuracy for deep…

Due to the high memory and computational costs associated with large language models (LLMs), model compression techniques such as quantization, which reduces inference costs, and parameter-efficient fine-tuning (PEFT) methods like Low-Rank…

Vision-Language-Action models (VLA) have demonstrated remarkable capabilities and promising potential in solving complex robotic manipulation tasks. However, their substantial parameter sizes and high inference latency pose significant…