LAUSR

Filter Pruning and Re-Initialization via Latent Space Clustering

Sign Up to like & get
recommendations!
0 Published in 2020 at "IEEE Access"

DOI: 10.1109/access.2020.3031031

Abstract: Filter pruning is prevalent for pruning-based model compression. Most filter pruning methods have two main issues: 1) the pruned network capability depends on that of source pretrained models, and 2) they do not consider that… read more here.

Keywords: space clustering; filter pruning; space; initialization ... See more keywords

Automated Filter Pruning Based on High-Dimensional Bayesian Optimization

Sign Up to like & get
recommendations!
1 Published in 2022 at "IEEE Access"

DOI: 10.1109/access.2022.3153025

Abstract: Filter pruning is necessary to efficiently deploy convolutional neural networks on edge devices that have limited computational resources and power budgets. With conventional filter pruning techniques, the same pruning rate is manually specified for different… read more here.

Keywords: filter pruning; bayesian optimization; dimensional bayesian; pruning rate ... See more keywords

Target Capacity Filter Pruning Method for Optimized Inference Time Based on YOLOv5 in Embedded Systems

Sign Up to like & get
recommendations!
2 Published in 2022 at "IEEE Access"

DOI: 10.1109/access.2022.3188323

Abstract: Recently, convolutional neural networks (CNNs), which exhibit excellent performance in the field of computer vision, have been in the spotlight. However, as the networks become wider for higher accuracy, the number of parameters and the… read more here.

Keywords: target capacity; time; inference time; filter pruning ... See more keywords

Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks

Sign Up to like & get
recommendations!
1 Published in 2020 at "IEEE Transactions on Cybernetics"

DOI: 10.1109/tcyb.2019.2933477

Abstract: Deeper and wider convolutional neural networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such overparameterized neural network has received increased attention. A typical pruning algorithm is a three-stage pipeline, i.e., training, pruning,… read more here.

Keywords: soft filter; neural networks; filter pruning; asymptotic soft ... See more keywords

Adaptive Filter Pruning via Sensitivity Feedback.

Sign Up to like & get
recommendations!
2 Published in 2023 at "IEEE transactions on neural networks and learning systems"

DOI: 10.1109/tnnls.2023.3246263

Abstract: Filter pruning is advocated for accelerating deep neural networks without dedicated hardware or libraries, while maintaining high prediction accuracy. Several works have cast pruning as a variant of l1 -regularized training, which entails two challenges:… read more here.

Keywords: filter pruning; sensitivity; accuracy; adaptive filter ... See more keywords