English
Related papers

Related papers: Reduced bit median quantization: A middle process …

200 papers

Post-training quantization (PTQ) of large language models (LLMs) holds the promise in reducing the prohibitive computational cost at inference time. Quantization of all weight, activation and key-value (KV) cache tensors to 4-bit without…

Machine Learning · Computer Science 2025-02-05 Utkarsh Saxena , Sayeh Sharify , Kaushik Roy , Xin Wang

Diffusion models have achieved great success in image synthesis through iterative noise estimation using deep neural networks. However, the slow inference, high memory consumption, and computation intensity of the noise estimation model…

Computer Vision and Pattern Recognition · Computer Science 2023-06-09 Xiuyu Li , Yijiang Liu , Long Lian , Huanrui Yang , Zhen Dong , Daniel Kang , Shanghang Zhang , Kurt Keutzer

Diffusion models excel in image generation but are computational and resource-intensive due to their reliance on iterative Markov chain processes, leading to error accumulation and limiting the effectiveness of naive compression techniques.…

Computer Vision and Pattern Recognition · Computer Science 2025-06-23 Beomseok Ko , Hyeryung Jang

Despite the proliferation of diverse hardware accelerators (e.g., NPU, TPU, DPU), deploying deep learning models on edge devices with fixed-point hardware is still challenging due to complex model quantization and conversion. Existing model…

Machine Learning · Computer Science 2023-08-07 Manasa Manohara , Sankalp Dayal , Tariq Afzal , Rahul Bakshi , Kahkuen Fu

Large-scale visual generative models have achieved remarkable performance. However, their high computational and memory costs make deployment challenging in resource-constrained scenarios, such as interactive applications and personal…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Yongsen Cheng , Kai Liu , Kaiwen Tao , Junxian Li , Zhixin Wang , Zhikai Chen , Renjing Pei , Yulun Zhang

This paper studies distributed algorithms for (strongly convex) composite optimization problems over mesh networks, subject to quantized communications. Instead of focusing on a specific algorithmic design, a black-box model is proposed,…

Optimization and Control · Mathematics 2022-05-19 Nicolò Michelusi , Gesualdo Scutari , Chang-Shen Lee

Could we compress images via standard codecs while avoiding visible artifacts? The answer is obvious -- this is doable as long as the bit budget is generous enough. What if the allocated bit-rate for compression is insufficient? Then…

Image and Video Processing · Electrical Eng. & Systems 2021-08-11 Hossein Talebi , Damien Kelly , Xiyang Luo , Ignacio Garcia Dorado , Feng Yang , Peyman Milanfar , Michael Elad

We propose a new transformer-based image and video tokenizer with Binary Spherical Quantization (BSQ). BSQ projects the high-dimensional visual embedding to a lower-dimensional hypersphere and then applies binary quantization. BSQ is (1)…

Computer Vision and Pattern Recognition · Computer Science 2024-06-12 Yue Zhao , Yuanjun Xiong , Philipp Krähenbühl

Real world re-identfication (ReID) algorithms aim to map new observations of an object to previously recorded instances. These systems are often constrained by quantity and size of the stored embeddings. To combat this scaling problem, we…

Computer Vision and Pattern Recognition · Computer Science 2024-05-24 Luke McDermott

Quantizing a floating-point neural network to its fixed-point representation is crucial for Learned Image Compression (LIC) because it improves decoding consistency for interoperability and reduces space-time complexity for implementation.…

Image and Video Processing · Electrical Eng. & Systems 2023-10-10 Junqi Shi , Ming Lu , Zhan Ma

Incorporating diffusion models in the image compression domain has the potential to produce realistic and detailed reconstructions, especially at extremely low bitrates. Previous methods focus on using diffusion models as expressive…

Image and Video Processing · Electrical Eng. & Systems 2024-10-10 Lucas Relic , Roberto Azevedo , Markus Gross , Christopher Schroers

The Magnetic Resonance Imaging (MRI) processing chain starts with a critical acquisition stage that provides raw data for reconstruction of images for medical diagnosis. This flow usually includes a near-lossless data compression stage that…

Image and Video Processing · Electrical Eng. & Systems 2020-11-10 Veronica Corona , Yehuda Dar , Guy Williams , Carola-Bibiane Schönlieb

Network quantization is an effective solution to compress deep neural networks for practical usage. Existing network quantization methods cannot sufficiently exploit the depth information to generate low-bit compressed network. In this…

Machine Learning · Computer Science 2018-12-18 Yuhui Xu , Yongzhuang Wang , Aojun Zhou , Weiyao Lin , Hongkai Xiong

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

Recent expansions in multimedia devices gather enormous amounts of real-time images for processing and inference. The images are first compressed using compression schemes, like JPEG, to reduce storage costs and power for transmitting the…

Image and Video Processing · Electrical Eng. & Systems 2024-06-25 Ming-Che Li , Archisman Ghosh , Shreyas Sen

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…

Image and Video Processing · Electrical Eng. & Systems 2020-03-16 Jooyoung Lee , Seunghyun Cho , Munchurl Kim

Large-scale pre-trained Vision-Language Models (VLMs) have gained prominence in various visual and multimodal tasks, yet the deployment of VLMs on downstream application platforms remains challenging due to their prohibitive requirements of…

Computer Vision and Pattern Recognition · Computer Science 2024-09-27 Huixin Sun , Runqi Wang , Yanjing Li , Xianbin Cao , Xiaolong Jiang , Yao Hu , Baochang Zhang

This paper proposes a method that enhances the compression performance of the current model under development for the upcoming MPEG standard on Feature Coding for Machines (FCM). This standard aims at providing inter-operable compressed…

Image and Video Processing · Electrical Eng. & Systems 2025-12-15 Juan Merlos , Fabien Racapé , Hyomin Choi , Mateen Ulhaq , Hari Kalva

Quantization is a widely used technique to compress and accelerate deep neural networks. However, conventional quantization methods use the same bit-width for all (or most of) the layers, which often suffer significant accuracy degradation…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Weihan Chen , Peisong Wang , Jian Cheng

Model reparameterization is a widely accepted technique for improving inference speed without compromising performance. However, current Post-training Quantization (PTQ) methods often lead to significant accuracy degradation when applied to…

Computer Vision and Pattern Recognition · Computer Science 2024-02-27 Luoming Zhang , Yefei He , Wen Fei , Zhenyu Lou , Weijia Wu , YangWei Ying , Hong Zhou
‹ Prev 1 3 4 5 6 7 10 Next ›