Papers Data Compression
“Data Compression” 태그가 달린 논문 459편 · 필터 해제
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
Transformers are slow to train on videos due to extremely large numbers of input tokens, even though many video tokens are repeated over time. Existing methods to remove such uninformative tokens either have significant …
Data CompressionSANN-PSZ: Spatially Adaptive Neural Network for Head-Tracked Personal Sound Zones
A deep learning framework for dynamically rendering personal sound zones (PSZs) with head tracking is presented, utilizing a spatially adaptive neural network (SANN) that inputs listeners' head coordinates and outputs PS…
Computational EfficiencyData AugmentationData CompressionMultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression
Large language models have drastically changed the prospects of AI by introducing technologies for more complex natural language processing. However, current methodologies to train such LLMs require extensive resources i…
Data CompressionIntegration of Communication and Computational Imaging
Communication enables the expansion of human visual perception beyond the limitations of time and distance, while computational imaging overcomes the constraints of depth and breadth. Although impressive achievements hav…
Data CompressionDMVC: Multi-Camera Video Compression Network aimed at Improving Deep Learning Accuracy
We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize huma…
Data CompressionVideo CompressionSemantic Information G Theory for Range Control with Tradeoff between Purposiveness and Efficiency
Recent advances in deep learning suggest that we need to maximize and minimize two different kinds of information simultaneously. The Information Max-Min (IMM) method has been used in deep learning, reinforcement learnin…
Data CompressionDeep Learningreinforcement-learningReinforcement LearningCompression using Discrete Multi-Level Divisor Transform for Heterogeneous Sensor Data
In recent years, multiple sensor-based devices and systems have been deployed in smart agriculture, industrial automation, E-Health, etc. The diversity of sensor data types and the amount of data pose critical challenges…
Data CompressionDiversityIn-context learning and Occam's razor
A central goal of machine learning is generalization. While the No Free Lunch Theorem states that we cannot obtain theoretical guarantees for generalization without further assumptions, in practice we observe that simple…
Data CompressionIn-Context LearningMatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection
KV cache has become a de facto technique for the inference of large language models (LLMs), where tensors of shape (layer number, head number, sequence length, feature dimension) are introduced to cache historical inform…
Data CompressionLarge Language Model Evaluation via Matrix Nuclear-Norm
As large language models (LLMs) continue to evolve, efficient evaluation metrics are vital for assessing their ability to compress information and reduce redundancy. While traditional metrics like Matrix Entropy offer va…
Computational EfficiencyData CompressionLanguage Model EvaluationLanguage Modeling+3Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach
Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding performance by utilizing rich semantic embed…
Data CompressionFacial Landmark DetectionFeature CompressionImage Compression+4Transformers learn variable-order Markov chains in-context
Large language models have demonstrated impressive in-context learning (ICL) capability. However, it is still unclear how the underlying transformers accomplish it, especially in more complex scenarios. Toward this goal,…
Data CompressionIn-Context LearningLanguage ModelingLanguage ModellingChannel-Aware Throughput Maximization for Cooperative Data Fusion in CAV
Connected and autonomous vehicles (CAVs) have garnered significant attention due to their extended perception range and enhanced sensing coverage. To address challenges such as blind spots and obstructions, CAVs employ v…
Autonomous VehiclesData CompressionAll-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation
Image coding for multi-task applications, catering to both human perception and machine vision, has been extensively investigated. Existing methods often rely on multiple task-specific encoder-decoder pairs, leading to h…
AllData CompressionFeature ImportanceImage Classification+2AlphaZip: Neural Network-Enhanced Lossless Text Compression
Data compression continues to evolve, with traditional information theory methods being widely used for compressing text, images, and videos. Recently, there has been growing interest in leveraging Generative AI for pred…
BenchmarkingData CompressionLanguage ModelingLanguage Modelling+2Anomaly Detection from a Tensor Train Perspective
We present a series of algorithms in tensor networks for anomaly detection in datasets, by using data compression in a Tensor Train representation. These algorithms consist of preserving the structure of normal data in c…
Anomaly DetectionData CompressionTensor NetworksData Compression using Rank-1 Lattices for Parameter Estimation in Machine Learning
The mean squared error and regularized versions of it are standard loss functions in supervised machine learning. However, calculating these losses for large data sets can be computationally demanding. Modifying an appro…
Data Compressionparameter estimationBlockchain-Enabled Variational Information Bottleneck for Data Extraction Based on Mutual Information in Internet of Vehicles
The Internet of Vehicles (IoV) network can address the issue of limited computing resources and data processing capabilities of individual vehicles, but it also brings the risk of privacy leakage to vehicle users. Applyi…
Data CompressionData Interactionk-mer-based approaches to bridging pangenomics and population genetics
Many commonly studied species now have more than one chromosome-scale genome assembly, revealing a large amount of genetic diversity previously missed by approaches that map short reads to a single reference. However, ma…
Data CompressionDiversityLearned Compression for Images and Point Clouds
Over the last decade, deep learning has shown great success at performing computer vision tasks, including classification, super-resolution, and style transfer. Now, we apply it to data compression to help build the next…
Data CompressionStyle TransferSuper-Resolution