paper-with-me

Papers

End-to-End Sensitivity-Based Filter Pruning

2022-04-15 · Zahra Babaiee, Lucas Liebenwein, Ramin Hasani, Daniela Rus, Radu Grosu

In this paper, we present a novel sensitivity-based filter pruning algorithm (SbF-Pruner) to learn the importance scores of filters of each layer end-to-end. Our method learns the scores from the filter weights, enabling it to account for the correlations between the filters of each layer. Moreover, by training the pruning scores of all layers simultaneously our method can account for layer interdependencies, which is essential to find a performant sparse sub-network. Our proposed method can train and generate a pruned network from scratch in a straightforward, one-stage training process without requiring a pretrained network. Ultimately, we do not need layer-specific hyperparameters and pre-defined layer budgets, since SbF-Pruner can implicitly determine the appropriate number of channels in each layer. Our experimental results on different network architectures suggest that SbF-Pruner outperforms advanced pruning methods. Notably, on CIFAR-10, without requiring a pretrained baseline network, we obtain 1.02% and 1.19% accuracy gain on ResNet56 and ResNet110, compared to the baseline reported for state-of-the-art pruning algorithms. This is while SbF-Pruner reduces parameter-count by 52.3% (for ResNet56) and 54% (for ResNet101), which is better than the state-of-the-art pruning algorithms with a high margin of 9.5% and 6.6%.

📄 PDF Abstract BibTeX arXiv:2204.07412

Code (0)

등록된 구현이 없습니다.

Tasks

Sensitivity

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Dynamic Sensitivity Filter Pruning using Multi-Agent Reinforcement Learning For DCNN's

2025-09-05 · Iftekhar Haider Chowdhury, Zaed Ikbal Syed, Ahmed Faizul Haque Dhrubo, Mohammad Abdul Qayum arxiv

Deep Convolutional Neural Networks have achieved state of the art performance across various computer vision tasks, however their practical deployment is limited by computational and memory overhead. This paper introduce…

Multi-agent Reinforcement Learning

Performance-aware Approximation of Global Channel Pruning for Multitask CNNs

2023-03-21 · Hancheng Ye, Bo Zhang, Tao Chen, Jiayuan Fan 외

Global channel pruning (GCP) aims to remove a subset of channels (filters) across different layers from a deep model without hurting the performance. Previous works focus on either single task model pruning or simply ada…

Model Compression

PFGDF: Pruning Filter via Gaussian Distribution Feature for Deep Neural Networks Acceleration

2020-06-23 · Jianrong Xu, Boyu Diao, Bifeng Cui, Kang Yang 외

Deep learning has achieved impressive results in many areas, but the deployment of edge intelligent devices is still very slow. To solve this problem, we propose a novel compression and acceleration method based on data …

Model Compression

Slimming Neural Networks using Adaptive Connectivity Scores

2020-06-22 · Madan Ravi Ganesh, Dawsin Blanchard, Jason J. Corso, Salimeh Yasaei Sekeh

In general, deep neural network (DNN) pruning methods fall into two categories: 1) Weight-based deterministic constraints, and 2) Probabilistic frameworks. While each approach has its merits and limitations there are a s…

Sensitivity

Magnitude and Similarity based Variable Rate Filter Pruning for Efficient Convolution Neural Networks

2022-12-27 · Applied Sciences 2022 12 · Deepak Ghimire, Seong-heum Kim

The superior performance of the recent deep learning models comes at the cost of a significant increase in computational complexity, memory use, and power consumption. Filter pruning is one of the effective neural networ…

Network PruningNeural Network Compression