paper-with-me

Papers

Softer Pruning, Incremental Regularization

2020-10-19 · Linhang Cai, Zhulin An, Chuanguang Yang, Yongjun Xu

Network pruning is widely used to compress Deep Neural Networks (DNNs). The Soft Filter Pruning (SFP) method zeroizes the pruned filters during training while updating them in the next training epoch. Thus the trained information of the pruned filters is completely dropped. To utilize the trained pruned filters, we proposed a SofteR Filter Pruning (SRFP) method and its variant, Asymptotic SofteR Filter Pruning (ASRFP), simply decaying the pruned weights with a monotonic decreasing parameter. Our methods perform well across various networks, datasets and pruning rates, also transferable to weight pruning. On ILSVRC-2012, ASRFP prunes 40% of the parameters on ResNet-34 with 1.63% top-1 and 0.68% top-5 accuracy improvement. In theory, SRFP and ASRFP are an incremental regularization of the pruned filters. Besides, We note that SRFP and ASRFP pursue better results while slowing down the speed of convergence.

📄 PDF Abstract BibTeX arXiv:2010.09498

Code (0)

등록된 구현이 없습니다.

Tasks

Network Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Structured Pruning for Efficient ConvNets via Incremental Regularization

2018-11-20 · NIPS Workshop CDNNRIA 2018 · Huan Wang, Qiming Zhang, Yuehai Wang, Haoji Hu

Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance loss. Despite its effectiveness, existing regularization-based parameter…

Structured Pruning for Efficient ConvNets via Incremental Regularization

2018-04-25 · Huan Wang, Qiming Zhang, Yuehai Wang, Yu Lu 외

Parameter pruning is a promising approach for CNN compression and acceleration by eliminating redundant model parameters with tolerable performance degrade. Despite its effectiveness, existing regularization-based parame…

Network Pruning

FedDIP: Federated Learning with Extreme Dynamic Pruning and Incremental Regularization

2023-09-13 · Qianyu Long, Christos Anagnostopoulos, Shameem Puthiya Parambath, Daning Bi

Federated Learning (FL) has been successfully adopted for distributed training and inference of large-scale Deep Neural Networks (DNNs). However, DNNs are characterized by an extremely large number of parameters, thus, y…

Federated Learning

Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment Classification

2021-06-21 · Binzong Geng, Min Yang, Fajie Yuan, Shupeng Wang 외

Lifelong learning capabilities are crucial for sentiment classifiers to process continuous streams of opinioned information on the Web. However, performing lifelong learning is non-trivial for deep neural networks as con…

Lifelong learningNetwork PruningSentiment AnalysisSentiment Classification

Soft Smoothness for Audio Inpainting Using a Latent Matrix Model in Delay-embedded Space

2022-03-18 · Tatsuya Yokota

Here, we propose a new reconstruction method of smooth time-series signals. A key concept of this study is not considering the model in signal space, but in delay-embedded space. In other words, we indirectly represent a…

Audio inpaintingTime SeriesTime Series Analysis