MaxQ: Multi-Axis Query for N: M Sparsity Network
N: M sparsity has received increasing attention due to its remarkable performance and
latency trade-off compared with structured and unstructured sparsity. However existing N: M …
latency trade-off compared with structured and unstructured sparsity. However existing N: M …
Enhanced network compression through tensor decompositions and pruning
Network compression techniques that combine tensor decompositions and pruning have
shown promise in leveraging the advantages of both strategies. In this work, we propose …
shown promise in leveraging the advantages of both strategies. In this work, we propose …
Weight-adaptive channel pruning for CNNs based on closeness-centrality modeling
Neural network pruning provides significant performance in reducing the resource
requirements for deploying deep convolutional models. Recent pruning techniques …
requirements for deploying deep convolutional models. Recent pruning techniques …
SUBP: Soft Uniform Block Pruning for 1N Sparse CNNs Multithreading Acceleration
The study of sparsity in Convolutional Neural Networks (CNNs) has become widespread to
compress and accelerate models in environments with limited resources. By constraining N …
compress and accelerate models in environments with limited resources. By constraining N …
BAP: bilateral asymptotic pruning for optimizing CNNs on image tasks
Pruning facilitates the acquisition of efficient convolutional neural networks (CNNs) tailored
for resource-limited environments. General pruning strategies for CNNs are typically based …
for resource-limited environments. General pruning strategies for CNNs are typically based …
Efficient tensor decomposition-based filter pruning
In this paper, we present CORING, which is short for effiCient tensOr decomposition-based
filteR prunING, a novel filter pruning methodology for neural networks. CORING is crafted to …
filteR prunING, a novel filter pruning methodology for neural networks. CORING is crafted to …
Dirichlet probability navigated fault detection via key-group memory auto-encoder under non-stationary working conditions
DY Weng, JW Zhu, Q Xuan - Information Sciences, 2024 - Elsevier
Real-time condition monitoring is the foundation of prognostics and health management
(PHM) for mechanical systems. Constraint by extravagant cost and insurmountable …
(PHM) for mechanical systems. Constraint by extravagant cost and insurmountable …
A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models
With the successful application of deep learning in communications systems, deep neural
networks are becoming the preferred method for signal classification. Although these …
networks are becoming the preferred method for signal classification. Although these …
MalDMTP: A Multi-tier Pooling Method for Malware Detection based on Graph Classification
L Kou, C Qiu, M Wang, H Liu, Y Du, J Zhang - Mobile Networks and …, 2024 - Springer
With the development and adoption of cloud platforms in various fields, malware attacks
have become a serious threat to the Internet cloud ecosystem. However, the pooling process …
have become a serious threat to the Internet cloud ecosystem. However, the pooling process …
CR-SFP: Learning Consistent Representation for Soft Filter Pruning
Soft filter pruning~(SFP) has emerged as an effective pruning technique for allowing pruned
filters to update and the opportunity for them to regrow to the network. However, this pruning …
filters to update and the opportunity for them to regrow to the network. However, this pruning …