paper-with-me

홈 › Papers

AdaDeep: A Usage-Driven, Automated Deep Model Compression Framework for Enabling Ubiquitous Intelligent Mobiles

2020-06-08 · Sicong Liu, Junzhao Du, Kaiming Nan, ZimuZhou, Atlas Wang, Yingyan Lin

Recent breakthroughs in Deep Neural Networks (DNNs) have fueled a tremendously growing demand for bringing DNN-powered intelligence into mobile platforms. While the potential of deploying DNNs on resource-constrained platforms has been demonstrated by DNN compression techniques, the current practice suffers from two limitations: 1) merely stand-alone compression schemes are investigated even though each compression technique only suit for certain types of DNN layers; and 2) mostly compression techniques are optimized for DNNs' inference accuracy, without explicitly considering other application-driven system performance (e.g., latency and energy cost) and the varying resource availability across platforms (e.g., storage and processing capability). To this end, we propose AdaDeep, a usage-driven, automated DNN compression framework for systematically exploring the desired trade-off between performance and resource constraints, from a holistic system level. Specifically, in a layer-wise manner, AdaDeep automatically selects the most suitable combination of compression techniques and the corresponding compression hyperparameters for a given DNN. Thorough evaluations on six datasets and across twelve devices demonstrate that AdaDeep can achieve up to $18.6\times$ latency reduction, $9.8\times$ energy-efficiency improvement, and $37.3\times$ storage reduction in DNNs while incurring negligible accuracy loss. Furthermore, AdaDeep also uncovers multiple novel combinations of compression techniques.

📄 PDF Abstract BibTeX arXiv:2006.04432

Code (0)

등록된 구현이 없습니다.

Tasks

Model Compression

Similar Papers 제목 키워드 기반

FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation

2022-08-25 · Yiming Bao, Xu Zhao, Dahong Qian

There exist challenging problems in 3D human pose estimation mission, such as poor performance caused by occlusion and self-occlusion. Recently, IMU-vision sensor fusion is regarded as valuable for solving these problems…

3D Human Pose EstimationPose EstimationSensor Fusion

Towards 1000-fold Electron Microscopy Image Compression for Connectomics via VQ-VAE with Transformer Prior

2025-10-31 · Fuming Yang, Yicong Li, Hanspeter Pfister, Jeff W. Lichtman 외 arxiv

Petascale electron microscopy (EM) datasets push storage, transfer, and downstream analysis toward their current limits. We present a vector-quantized variational autoencoder-based (VQ-VAE) compression framework for EM t…

Image Compression

R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search

2025-05-22 · Yibo Wang, Li Shen, Huanjin Yao, Tiansheng Huang 외

Chain-of-Thought (CoT) reasoning enhances large language models (LLMs) by enabling step-by-step problem-solving, yet its extension to Long-CoT introduces substantial computational overhead due to increased token length. …

AgentGC: Evolutionary Learning-based Lossless Compression for Genomics Data with LLM-driven Multiple Agent

2026-01-20 · Sun Hui, Ding Yanfeng, Huidong Ma, Chang Xu 외 arxiv

Lossless compression has made significant advancements in Genomics Data (GD) storage, sharing and management. Current learning-based methods are non-evolvable with problems of low-level compression modeling, limited adap…

SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning

2026-02-26 · Sanjay Kariyappa, G. Edward Suh arxiv

Long-running agentic tasks, such as deep research, require multi-hop reasoning over information distributed across multiple webpages and documents. In such tasks, the LLM context is dominated by tokens from external retr…