paper-with-me

Papers

PCAS: Pruning Channels with Attention Statistics for Deep Network Compression

2018-06-14 · Kohei Yamamoto, Kurato Maeno

Compression techniques for deep neural networks are important for implementing them on small embedded devices. In particular, channel-pruning is a useful technique for realizing compact networks. However, many conventional methods require manual setting of compression ratios in each layer. It is difficult to analyze the relationships between all layers, especially for deeper models. To address these issues, we propose a simple channel-pruning technique based on attention statistics that enables to evaluate the importance of channels. We improved the method by means of a criterion for automatic channel selection, using a single compression ratio for the entire model in place of per-layer model analysis. The proposed approach achieved superior performance over conventional methods with respect to accuracy and the computational costs for various models and datasets. We provide analysis results for behavior of the proposed criterion on different datasets to demonstrate its favorable properties for channel pruning.

📄 PDF Abstract BibTeX arXiv:1806.05382

Code (0)

등록된 구현이 없습니다.

Tasks

channel selection

Similar Papers 제목 키워드 기반

UniCP: A Unified Caching and Pruning Framework for Efficient Video Generation

2025-02-06 · Wenzhang Sun, Qirui Hou, Donglin Di, Jiahui Yang 외

Diffusion Transformers (DiT) excel in video generation but encounter significant computational challenges due to the quadratic complexity of attention. Notably, attention differences between adjacent diffusion steps foll…

Computational EfficiencyVideo Generation

Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks

2020-02-23 · Sai Aparna Aketi, Sourjya Roy, Anand Raghunathan, Kaushik Roy

The enormous inference cost of deep neural networks can be scaled down by network compression. Pruning is one of the predominant approaches used for deep network compression. However, existing pruning techniques have one…

Model Compression

Group channel pruning and spatial attention distilling for object detection

2023-06-02 · Yun Chu, Pu Li, Yong Bai, Zhuhua Hu 외

Due to the over-parameterization of neural networks, many model compression methods based on pruning and quantization have emerged. They are remarkable in reducing the size, parameter number, and computational complexity…

Knowledge DistillationModel Compressionobject-detectionObject Detection+1

Cascaded Multi-Granularity Pruning for On-Device LLM Inference in Industrial IoT

2026-06-25 · Jinghan Wang, Yanjun Chen, Wei Zhang, Xiaotong Huang 외 arxiv

Deploying large language models (LLMs) on Industrial Internet of Things (IIoT) edge devices demands extreme compression, yet existing structured pruning methods collapse at high compression ratios due to one-shot importa…

Fault Diagnosis

Dirichlet Pruning for Neural Network Compression

2020-11-10 · Kamil Adamczewski, Mijung Park

We introduce Dirichlet pruning, a novel post-processing technique to transform a large neural network model into a compressed one. Dirichlet pruning is a form of structured pruning that assigns the Dirichlet distribution…

Neural Network CompressionVariational Inference