activity
20212025
most citedSub-network Multi-objective Evolutionary Algorithm for Filter Pruning

1 citations · 2 across the 5 of their papers we have counts for

collaborators

6 papers

eess.SP2025

CF-Net: A Cross-Feature Reconstruction Network for High-Accuracy 1-Bit Target Classification

Jundong Qi, Weize Sun, Shaowu Chen +2

Target classification is a fundamental task in radar systems, and its performance critically depends on the quantization precision of the signal. While high-precision quantization…

cs.CV2025

Optimal Brain Connection: Towards Efficient Structural Pruning

Shaowu Chen, Wei Ma, Binhua Huang +5

Structural pruning has been widely studied for its effectiveness in compressing neural networks. However, existing methods often neglect the interconnections among parameters. To a…

cs.LG2023

POCKET: Pruning Random Convolution Kernels for Time Series Classification from a Feature Selection Perspective

Shaowu Chen, Weize Sun, Lei Huang +3

In recent years, two competitive time series classification models, namely, ROCKET and MINIROCKET, have garnered considerable attention due to their low training cost and high accu…

cs.CV2023

WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks

Shaowu Chen, Weize Sun, Lei Huang

Filter pruning has attracted increasing attention in recent years for its capacity in compressing and accelerating convolutional neural networks. Various data-independent criteria,…

cs.NE2022★ 1 cited

Sub-network Multi-objective Evolutionary Algorithm for Filter Pruning

Xuhua Li, Weize Sun, Lei Huang +1

Filter pruning is a common method to achieve model compression and acceleration in deep neural networks (DNNs).Some research regarded filter pruning as a combinatorial optimization…

cs.CV2021★ 1 cited

Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression

Shaowu Chen, Jiahao Zhou, Weize Sun +1

Deep convolutional neural networks (CNNs) with a large number of parameters require intensive computational resources, and thus are hard to be deployed in resource-constrained plat…