Papers Data Compression
“Data Compression” 태그가 달린 논문 459편 · 필터 해제
Evaluating Large Language Models for Generalization and Robustness via Data Compression
Existing methods for evaluating large language models face challenges such as data contamination, sensitivity to prompts, and the high cost of benchmark creation. To address this, we propose a lossless data compression b…
ArticlesData CompressionDiff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models
Large Language Models (LLMs) have transformed natural language processing and extended their powerful capabilities to multi-modal domains. As LLMs continue to advance, it is crucial to develop diverse and appropriate met…
Data CompressionLanguage ModellingLarge Language ModelResidual Quantization with Implicit Neural Codebooks
Vector quantization is a fundamental operation for data compression and vector search. To obtain high accuracy, multi-codebook methods represent each vector using codewords across several codebooks. Residual quantization…
Data CompressionQuantizationConditional Neural Video Coding with Spatial-Temporal Super-Resolution
This document is an expanded version of a one-page abstract originally presented at the 2024 Data Compression Conference. It describes our proposed method for the video track of the Challenge on Learned Image Compression…
Data CompressionImage CompressionMotion EstimationSuper-ResolutionRSCNet: Dynamic CSI Compression for Cloud-based WiFi Sensing
WiFi-enabled Internet-of-Things (IoT) devices are evolving from mere communication devices to sensing instruments, leveraging Channel State Information (CSI) extraction capabilities. Nevertheless, resource-constrained Io…
Data CompressionHuman Activity RecognitionDepth Over RGB: Automatic Evaluation of Open Surgery Skills Using Depth Camera
Purpose: In this paper, we present a novel approach to the automatic evaluation of open surgery skills using depth cameras. This work is intended to show that depth cameras achieve similar results to RGB cameras, which i…
Action SegmentationData Compressionobject-detectionObject Detection+1Memory Efficient Corner Detection for Event-driven Dynamic Vision Sensors
Event cameras offer low-latency and data compression for visual applications, through event-driven operation, that can be exploited for edge processing in tiny autonomous agents. Robust, accurate and low latency extracti…
Data CompressionEdge-computingMachine Perceptual Quality: Evaluating the Impact of Severe Lossy Compression on Audio and Image Models
In the field of neural data compression, the prevailing focus has been on optimizing algorithms for either classical distortion metrics, such as PSNR or SSIM, or human perceptual quality. With increasing amounts of data …
Data Compressionimage-classificationImage ClassificationImage Segmentation+5MGARD: A multigrid framework for high-performance, error-controlled data compression and refactoring
We describe MGARD, a software providing MultiGrid Adaptive Reduction for floating-point scientific data on structured and unstructured grids. With exceptional data compression capability and precise error control, MGARD …
Data CompressionGPUManagementTransformer Masked Autoencoders for Next-Generation Wireless Communications: Architecture and Opportunities
Next-generation communication networks are expected to exploit recent advances in data science and cutting-edge communications technologies to improve the utilization of the available communications resources. In this ar…
Data CompressionSpatiotemporally adaptive compression for scientific dataset with feature preservation -- a case study on simulation data with extreme climate events analysis
Scientific discoveries are increasingly constrained by limited storage space and I/O capacities. For time-series simulations and experiments, their data often need to be decimated over timesteps to accommodate storage an…
Data CompressionFFCA-Net: Stereo Image Compression via Fast Cascade Alignment of Side Information
Multi-view compression technology, especially Stereo Image Compression (SIC), plays a crucial role in car-mounted cameras and 3D-related applications. Interestingly, the Distributed Source Coding (DSC) theory suggests th…
Data CompressionDecoderImage CompressionPatch MatchingOn Robust Wasserstein Barycenter: The Model and Algorithm
The Wasserstein barycenter problem is to compute the average of $m$ given probability measures, which has been widely studied in many different areas; however, real-world data sets are often noisy and huge, which impedes…
Computational EfficiencyData CompressionCompact 3D Scene Representation via Self-Organizing Gaussian Grids
3D Gaussian Splatting has recently emerged as a highly promising technique for modeling of static 3D scenes. In contrast to Neural Radiance Fields, it utilizes efficient rasterization allowing for very fast rendering at …
3DGS3D Scene ReconstructionData Compression+3IntraSeismic: a coordinate-based learning approach to seismic inversion
Seismic imaging is the numerical process of creating a volumetric representation of the subsurface geological structures from elastic waves recorded at the surface of the Earth. As such, it is widely utilized in the ener…
Data CompressionSeismic ImagingSeismic InversionUncertainty QuantificationTowards Neuromorphic Compression based Neural Sensing for Next-Generation Wireless Implantable Brain Machine Interface
This work introduces a neuromorphic compression based neural sensing architecture with address-event representation inspired readout protocol for massively parallel, next-gen wireless iBMI. The architectural trade-offs a…
Data CompressionExplainable Trajectory Representation through Dictionary Learning
Trajectory representation learning on a network enhances our understanding of vehicular traffic patterns and benefits numerous downstream applications. Existing approaches using classic machine learning or deep learning …
Data CompressionDictionary LearningRepresentation LearningCommunication Cost Reduction for Subgraph Counting under Local Differential Privacy via Hash Functions
We suggest the use of hash functions to cut down the communication costs when counting subgraphs under edge local differential privacy. While various algorithms exist for computing graph statistics, including the count o…
Data CompressionSubgraph CountingVariational Auto-Encoder Based Deep Learning Technique For Filling Gaps in Reacting PIV Data
In this study, a deep learning based conditional density estimation technique known as conditional variational auto-encoder (CVAE) is used to fill gaps typically observed in particle image velocimetry (PIV) measurements …
Data CompressionDensity EstimationMoEC: Mixture of Experts Implicit Neural Compression
Emerging Implicit Neural Representation (INR) is a promising data compression technique, which represents the data using the parameters of a Deep Neural Network (DNN). Existing methods manually partition a complex scene …
Data CompressionMixture-of-Experts