paper-with-me

Papers

Progressive Channel-Shrinking Network

2023-04-01 · Jianhong Pan, Siyuan Yang, Lin Geng Foo, Qiuhong Ke, Hossein Rahmani, Zhipeng Fan, Jun Liu

Currently, salience-based channel pruning makes continuous breakthroughs in network compression. In the realization, the salience mechanism is used as a metric of channel salience to guide pruning. Therefore, salience-based channel pruning can dynamically adjust the channel width at run-time, which provides a flexible pruning scheme. However, there are two problems emerging: a gating function is often needed to truncate the specific salience entries to zero, which destabilizes the forward propagation; dynamic architecture brings more cost for indexing in inference which bottlenecks the inference speed. In this paper, we propose a Progressive Channel-Shrinking (PCS) method to compress the selected salience entries at run-time instead of roughly approximating them to zero. We also propose a Running Shrinking Policy to provide a testing-static pruning scheme that can reduce the memory access cost for filter indexing. We evaluate our method on ImageNet and CIFAR10 datasets over two prevalent networks: ResNet and VGG, and demonstrate that our PCS outperforms all baselines and achieves state-of-the-art in terms of compression-performance tradeoff. Moreover, we observe a significant and practical acceleration of inference.

📄 PDF Abstract BibTeX arXiv:2304.00280

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Residual Connection 설명 없음
Average Pooling 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…

Similar Papers 제목 키워드 기반

BS-NAS: Broadening-and-Shrinking One-Shot NAS with Searchable Numbers of Channels

2020-03-22 · Zan Shen, Jiang Qian, Bojin Zhuang, Shaojun Wang 외

One-Shot methods have evolved into one of the most popular methods in Neural Architecture Search (NAS) due to weight sharing and single training of a supernet. However, existing methods generally suffer from two issues: …

Neural Architecture Search

Angle-based Search Space Shrinking for Neural Architecture Search

2020-04-28 · ECCV 2020 8 · Yiming Hu, Yuding Liang, Zichao Guo, Ruosi Wan 외

In this work, we present a simple and general search space shrinking method, called Angle-Based search space Shrinking (ABS), for Neural Architecture Search (NAS). Our approach progressively simplifies the original searc…

Neural Architecture Search

CAKES: Channel-wise Automatic KErnel Shrinking for Efficient 3D Networks

2020-03-28 · Qihang Yu, Yingwei Li, Jieru Mei, Yuyin Zhou 외

3D Convolution Neural Networks (CNNs) have been widely applied to 3D scene understanding, such as video analysis and volumetric image recognition. However, 3D networks can easily lead to over-parameterization which incur…

3D Medical Imaging SegmentationAction RecognitionMedical Image SegmentationNeural Architecture Search+2

Breaking the Memory Wall for Heterogeneous Federated Learning via Progressive Training

2024-04-20 · Yebo Wu, Li Li, Chengzhong Xu

This paper presents ProFL, a new framework that effectively addresses the memory constraints in FL. Rather than updating the full model during local training, ProFL partitions the model into blocks based on its original …

Federated Learning

HSCoNAS: Hardware-Software Co-Design of Efficient DNNs via Neural Architecture Search

2021-03-11 · Xiangzhong Luo, Di Liu, Shuo Huai, Weichen Liu

In this paper, we present a novel multi-objective hardware-aware neural architecture search (NAS) framework, namely HSCoNAS, to automate the design of deep neural networks (DNNs) with high accuracy but low latency upon t…

CPUGPUHardware Aware Neural Architecture SearchNeural Architecture Search