中文
相关论文

相关论文: Efficient Learned Image Compression without Entrop…

200 篇论文

Augmenting Large Language Models (LLMs) with retrieved external knowledge has proven effective for improving the factual accuracy of generated responses. Despite their success, retrieval-augmented LLMs still face the distractibility issue,…

计算与语言 · 计算机科学 2025-02-18 Zexuan Qiu , Zijing Ou , Bin Wu , Jingjing Li , Aiwei Liu , Irwin King

We present an end-to-end image compression system based on compressive sensing. The presented system integrates the conventional scheme of compressive sampling and reconstruction with quantization and entropy coding. The compression…

计算机视觉与模式识别 · 计算机科学 2020-01-22 Xin Yuan , Raziel Haimi-Cohen

Lossy image compression is generally formulated as a joint rate-distortion optimization to learn encoder, quantizer, and decoder. However, the quantizer is non-differentiable, and discrete entropy estimation usually is required for rate…

计算机视觉与模式识别 · 计算机科学 2017-09-20 Mu Li , Wangmeng Zuo , Shuhang Gu , Debin Zhao , David Zhang

Recently, learned image compression methods have been actively studied. Among them, entropy-minimization based approaches have achieved superior results compared to conventional image codecs such as BPG and JPEG2000. However, the quality…

图像与视频处理 · 电气工程与系统科学 2020-03-16 Jooyoung Lee , Seunghyun Cho , Munchurl Kim

This paper investigates a novel lossy compression framework operating under logarithmic loss, designed to handle situations where the reconstruction distribution diverges from the source distribution. This framework is especially relevant…

机器学习 · 计算机科学 2024-10-30 M. Reza Ebrahimi , Jun Chen , Ashish Khisti

Light field imaging is characterized by capturing brightness, color, and directional information of light rays in a scene. This leads to image representations with huge amount of data that require efficient coding schemes. In this paper,…

计算机视觉与模式识别 · 计算机科学 2019-02-01 Hadi Amirpour , Antonio Pinheiro , Manuela Pereira , Mohammad Ghanbari

Learned Image Compression (LIC) has recently become the trending technique for image transmission due to its notable performance. Despite its popularity, the robustness of LIC with respect to the quality of image reconstruction remains…

计算机视觉与模式识别 · 计算机科学 2023-06-05 Yang Sui , Zhuohang Li , Ding Ding , Xiang Pan , Xiaozhong Xu , Shan Liu , Zhenzhong Chen

The framework of dominant learned video compression methods is usually composed of motion prediction modules as well as motion vector and residual image compression modules, suffering from its complex structure and error propagation…

图像与视频处理 · 电气工程与系统科学 2021-04-14 Zhenhong Sun , Zhiyu Tan , Xiuyu Sun , Fangyi Zhang , Dongyang Li , Yichen Qian , Hao Li

Federated learning (FL) enables collaborative model training without exposing clients' private data, but its deployment is often constrained by the communication cost of transmitting gradients between clients and the central server,…

机器学习 · 计算机科学 2025-11-11 Zhijing Ye , Sheng Di , Jiamin Wang , Zhiqing Zhong , Zhaorui Zhang , Xiaodong Yu

As a fundamental visual attribute, image complexity significantly influences both human perception and the performance of computer vision models. However, accurately assessing and quantifying image complexity remains a challenging task. (1)…

计算机视觉与模式识别 · 计算机科学 2025-04-28 Shipeng Liu , Liang Zhao , Dengfeng Chen

Efficiently transferring Learned Image Compression (LIC) model from human perception to machine perception is an emerging challenge in vision-centric representation learning. Existing approaches typically adapt LIC to downstream tasks in a…

计算机视觉与模式识别 · 计算机科学 2025-08-05 Jiancheng Zhao , Xiang Ji , Yinqiang Zheng

Neural compression has brought tremendous progress in designing lossy compressors with good rate-distortion (RD) performance at low complexity. Thus far, neural compression design involves transforming the source to a latent vector, which…

信息论 · 计算机科学 2025-07-15 Eric Lei , Hamed Hassani , Shirin Saeedi Bidokhti

Recent advancements in learned image compression (LIC) methods have demonstrated superior performance over traditional hand-crafted codecs. These learning-based methods often employ convolutional neural networks (CNNs) or Transformer-based…

计算机视觉与模式识别 · 计算机科学 2024-08-08 Hamidreza Soltani , Erfan Ghasemi

This paper introduces Locally Adaptive Neural Context Estimation (LANCE), a novel extension for overfitted image compression (OIC) frameworks like Cool-Chic. While traditional OIC methods rely on lightweight autoregressive networks with…

图像与视频处理 · 电气工程与系统科学 2026-05-21 Martin Benjak , Jörn Ostermann

Traditional video compression technologies have been developed over decades in pursuit of higher coding efficiency. Efficient temporal information representation plays a key role in video coding. Thus, in this paper, we propose to exploit…

图像与视频处理 · 电气工程与系统科学 2019-12-16 Haojie Liu , Han shen , Lichao Huang , Ming Lu , Tong Chen , Zhan Ma

The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video…

图像与视频处理 · 电气工程与系统科学 2024-07-08 Farhad Pakdaman , Moncef Gabbouj

This paper proposes a novel entropy encoding technique for lossless data compression. Representing a message string by its lexicographic index in the permutations of its symbols results in a compressed version matching Shannon entropy of…

信息论 · 计算机科学 2017-03-24 Abu Bakar Siddique

Large language models (LLMs) have demonstrated transformative capabilities across diverse artificial intelligence applications, yet their deployment is hindered by substantial memory and computational demands, especially in…

硬件体系结构 · 计算机科学 2025-05-13 Feng Cheng , Cong Guo , Chiyue Wei , Junyao Zhang , Changchun Zhou , Edward Hanson , Jiaqi Zhang , Xiaoxiao Liu , Hai "Helen" Li , Yiran Chen

One critical component in lossy deep image compression is the entropy model, which predicts the probability distribution of the quantized latent representation in the encoding and decoding modules. Previous works build entropy models upon…

图像与视频处理 · 电气工程与系统科学 2023-03-16 Yichen Qian , Ming Lin , Xiuyu Sun , Zhiyu Tan , Rong Jin

A mainstream type of current self-supervised learning methods pursues a general-purpose representation that can be well transferred to downstream tasks, typically by optimizing on a given pretext task such as instance discrimination. In…

计算机视觉与模式识别 · 计算机科学 2022-10-21 Xin Liu , Zhongdao Wang , Yali Li , Shengjin Wang