English
Related papers

Related papers: Parallelized Rate-Distortion Optimized Quantizatio…

200 papers

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…

Computer Vision and Pattern Recognition · Computer Science 2017-08-04 Yinpeng Dong , Renkun Ni , Jianguo Li , Yurong Chen , Jun Zhu , Hang Su

Service providers must encode a large volume of noisy videos to meet the demand for user-generated content (UGC) in online video-sharing platforms. However, low-quality UGC challenges conventional codecs based on rate-distortion…

Image and Video Processing · Electrical Eng. & Systems 2025-05-22 Samuel Fernández-Menduiña , Xin Xiong , Eduardo Pavez , Antonio Ortega , Neil Birkbeck , Balu Adsumilli

Learned video coding (LVC) has recently achieved superior coding performance. In this paper, we model the rate-quality (R-Q) relationship for learned video coding by a parametric function. We learn a neural network, termed RQNet, to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-03 Sang NguyenQuang , Cheng-Wei Chen , Xiem HoangVan , Wen-Hsiao Peng

Recent state-of-the-art neural audio compression models have progressively adopted residual vector quantization (RVQ). Despite this success, these models employ a fixed number of codebooks per frame, which can be suboptimal in terms of…

Hardware-friendly network quantization (e.g., binary/uniform quantization) can efficiently accelerate the inference and meanwhile reduce memory consumption of the deep neural networks, which is crucial for model deployment on…

Computer Vision and Pattern Recognition · Computer Science 2019-08-15 Ruihao Gong , Xianglong Liu , Shenghu Jiang , Tianxiang Li , Peng Hu , Jiazhen Lin , Fengwei Yu , Junjie Yan

The rate-distortion performance of neural image compression models has exceeded the state-of-the-art for non-learned codecs, but neural codecs are still far from widespread deployment and adoption. The largest obstacle is having efficient…

Computer Vision and Pattern Recognition · Computer Science 2023-11-23 David Minnen , Nick Johnston

Conventional video compression (VC) methods are based on motion compensated transform coding, and the steps of motion estimation, mode and quantization parameter selection, and entropy coding are optimized individually due to the…

Image and Video Processing · Electrical Eng. & Systems 2021-12-20 M. Akın Yılmaz , A. Murat Tekalp

Neural video compression (NVC) has demonstrated superior compression efficiency, yet effective rate control remains a significant challenge due to complex temporal dependencies. Existing rate control schemes typically leverage frame content…

Image and Video Processing · Electrical Eng. & Systems 2026-02-03 Wuyang Cong , Junqi Shi , Lizhong Wang , Weijing Shi , Ming Lu , Hao Chen , Zhan Ma

Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of…

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…

Computer Vision and Pattern Recognition · Computer Science 2019-04-09 Kuan Wang , Zhijian Liu , Yujun Lin , Ji Lin , Song Han

This paper introduces a dual-critic reinforcement learning (RL) framework to address the problem of frame-level bit allocation in HEVC/H.265. The objective is to minimize the distortion of a group of pictures (GOP) under a rate constraint.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Yung-Han Ho , Guo-Lun Jin , Yun Liang , Wen-Hsiao Peng , Xiaobo Li

Post-training Neural Network (NN) model compression is an attractive approach for deploying large, memory-consuming models on devices with limited memory resources. In this study, we investigate the rate-distortion tradeoff for NN model…

Machine Learning · Computer Science 2024-12-03 Joseph Kampeas , Yury Nahshan , Hanoch Kremer , Gil Lederman , Shira Zaloshinski , Zheng Li , Emir Haleva

Large language models (LLMs) have shown strong performance across diverse tasks, but their inference with long input contexts is bottlenecked by memory size and bandwidth. The Key-Value (KV) cache size grows linearly with sequence length…

Machine Learning · Computer Science 2026-05-12 Junkai Zhang , Hang Guo , Luca Benini , Yawei Li

Non-reference metrics (NRMs) can assess the visual quality of images and videos without a reference, making them well-suited for the evaluation of user-generated content. Nonetheless, rate-distortion optimization (RDO) in video coding is…

Image and Video Processing · Electrical Eng. & Systems 2026-02-18 Xin Xiong , Samuel Fernández-Menduiña , Eduardo Pavez , Antonio Ortega , Neil Birkbeck , Balu Adsumilli

Linear block transform coding remains a fundamental component of image and video compression. Although the Discrete Cosine Transform (DCT) is widely employed in all current compression standards, its sub-optimality has sparked ongoing…

Image and Video Processing · Electrical Eng. & Systems 2024-11-28 Alessandro Gnutti , Chia-Hao Kao , Wen-Hsiao Peng , Riccardo Leonardi

This work introduces NeuroQuant, a novel post-training quantization (PTQ) approach tailored to non-generalized Implicit Neural Representations for variable-rate Video Coding (INR-VC). Unlike existing methods that require extensive weight…

Image and Video Processing · Electrical Eng. & Systems 2025-02-18 Junqi Shi , Zhujia Chen , Hanfei Li , Qi Zhao , Ming Lu , Tong Chen , Zhan Ma

Built upon vector quantization (VQ), discrete audio codec models have achieved great success in audio compression and auto-regressive audio generation. However, existing models face substantial challenges in perceptual quality and signal…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-20 Zhikang Niu , Sanyuan Chen , Long Zhou , Ziyang Ma , Xie Chen , Shujie Liu

In High Efficiency Video Coding (HEVC), excellent rate-distortion (RD) performance is achieved in part by having a flexible quadtree coding unit (CU) partition and a large number of intra-prediction modes. Such an excellent RD performance…

Image and Video Processing · Electrical Eng. & Systems 2020-04-22 Zhibo Chen , Jun Shi , Weiping Li

A broad range of technologies rely on remote inference, wherein data acquired is conveyed over a communication channel for inference in a remote server. Communication between the participating entities is often carried out over rate-limited…

Signal Processing · Electrical Eng. & Systems 2025-01-07 Eyal Fishel , May Malka , Shai Ginzach , Nir Shlezinger

The Residual Quantization (RQ) framework is revisited where the quantization distortion is being successively reduced in multi-layers. Inspired by the reverse-water-filling paradigm in rate-distortion theory, an efficient regularization on…

Machine Learning · Computer Science 2017-05-02 Sohrab Ferdowsi , Slava Voloshynovskiy , Dimche Kostadinov