Results 251 to 260 of about 937,847 (306)

Lossless compression of Peanoscanned images

Journal of Electronic Imaging, 1994
Peanoscanning was used to obtain the pixels from an image by following a scan path described by a space-filling curve, the Peano-Hilbert curve. The Peanoscanned data were then compressed without loss of information by direct Huffrnan, arithmetic, and Lernpel-Ziv-Welch coding, as well as predictive and transform coding.
Joseph A. Provine, Rangaraj M. Rangayyan
openaire   +1 more source

GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM

arXiv.org
Key-value (KV) caching has become the de-facto to accelerate generation speed for large language models (LLMs) inference. However, the growing cache demand with increasing sequence length has transformed LLM inference to be a memory bound problem ...
Hao Kang, Qingru Zhang, Souvik Kundu, Geonhwa Jeong, Zaoxing Liu, Tushar Krishna, Tuo Zhao   +6 more
semanticscholar   +1 more source

Lossless Compression of Random Forests

Journal of Computer Science and Technology, 2019
Ensemble methods are among the state-of-the-art predictive modeling approaches. Applied to modern big data, these methods often require a large number of sub-learners, where the complexity of each learner typically grows with the size of the dataset. This phenomenon results in an increasing demand for storage space, which may be very costly.
Amichai Painsky, Saharon Rosset
openaire   +1 more source

Lossless Compression of Deep Neural Networks

Integration of AI and OR Techniques in Constraint Programming, 2020
Deep neural networks have been successful in many predictive modeling tasks, such as image and language recognition, where large neural networks are often used to obtain good accuracy.
Thiago Serra, Abhinav Kumar, Srikumar Ramalingam   +2 more
semanticscholar   +1 more source

Learning Scalable ℓ∞-constrained Near-lossless Image Compression via Joint Lossy Image and Residual Compression

Computer Vision and Pattern Recognition, 2021
We propose a novel joint lossy image and residual compression framework for learning ℓ∞-constrained near-lossless image compression. Specifically, we obtain a lossy reconstruction of the raw image through lossy image compression and uniformly quantize ...
Yuanchao Bai, Xianming Liu, W. Zuo, Yaowei Wang, Xiangyang Ji   +4 more
semanticscholar   +1 more source

Lossless compression of video sequences

IEEE Transactions on Communications, 1996
We investigate lossless compression schemes for video sequences. A simple adaptive prediction scheme is presented that exploits temporal correlations or spectral correlations in addition to spatial correlations. It is seen that even with motion compensation, schemes that utilize only temporal correlations do not perform significantly better than ...
Nasir D. Memon, Khalid Sayood
openaire   +1 more source

ZipNN: Lossless Compression for AI Models

IEEE International Conference on Cloud Computing
With the growth of model sizes and the scale of their deployment, their sheer size burdens the infrastructure requiring more network and more storage to accommodate these.
Moshe Hershcovitch, Andrew Wood, Leshem Choshen, Guy Girmonsky, Roy Leibovitz, Ilias Ennmouri, Michal Malka, Peter Chin, S. Sundararaman, Danny Harnik   +9 more
semanticscholar   +1 more source

Lossless compression of AVIRIS images

IEEE Transactions on Image Processing, 1996
Adaptive DPCM methods using linear prediction are described for the lossless compression of hyperspectral (224-band) images recorded by the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS). The methods have two stages-predictive decorrelation (which produces residuals) and residual encoding.
R. E. Roger, Michael C. Cavenor
openaire   +2 more sources

Lossless compression of seismic data

SEG Technical Program Expanded Abstracts 1996, 1996
A lossless method for seismic data compression has been developed. The method uses the idea of converting a signal data compression problem into a text compression problem. The conversion is based on data slicing, a reformatting process where the binary representation of a data set is rearranged, effectively separating compressible from uncompressible ...
Jeričević, Željko, Sitton, Gary A.
openaire   +2 more sources

Multiresolution lossless compression scheme

Proceedings of 3rd IEEE International Conference on Image Processing, 2002
A multiresolution lossless image compression scheme based on several new tools will be presented in this paper. An improved multiresolution Haar transform will be developed, combined with pre- and post-processing and with a new entropy coder, to give the overall compression scheme.
Patrick Piscaglia, Benoît Macq
openaire   +1 more source