paper-with-me

Papers

On Implicit Filter Level Sparsity in Convolutional Neural Networks

2018-11-29 · CVPR 2019 6 · Dushyant Mehta, Kwang In Kim, Christian Theobalt

We investigate filter level sparsity that emerges in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay. We conduct an extensive experimental study casting our initial findings into hypotheses and conclusions about the mechanisms underlying the emergent filter level sparsity. This study allows new insight into the performance gap obeserved between adapative and non-adaptive gradient descent methods in practice. Further, analysis of the effect of training strategies and hyperparameters on the sparsity leads to practical suggestions in designing CNN training strategies enabling us to explore the tradeoffs between feature selectivity, network capacity, and generalization performance. Lastly, we show that the implicit sparsity can be harnessed for neural network speedup at par or better than explicit sparsification / pruning approaches, with no modifications to the typical training pipeline required.

📄 PDF Abstract BibTeX arXiv:1811.12495

Code (0)

등록된 구현이 없습니다.

Tasks

L2 Regularization

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Emergence of Implicit Filter Sparsity in Convolutional Neural Networks

2019-05-17 · ICML Workshop Deep_Phenomen 2019 6 · Dushyant Mehta, Kwang In Kim, Christian Theobalt

We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained using adaptive gradient descent techniques with L2 regulariza…

L2 Regularization

Implicit Filter Sparsification In Convolutional Neural Networks

2019-05-13 · Dushyant Mehta, Kwang In Kim, Christian Theobalt

We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularizati…

L2 Regularization

Nonlocality-Reinforced Convolutional Neural Networks for Image Denoising

2018-03-06 · Cristóvão Cruz, Alessandro Foi, Vladimir Katkovnik, Karen Egiazarian

We introduce a paradigm for nonlocal sparsity reinforced deep convolutional neural network denoising. It is a combination of a local multiscale denoising by a convolutional neural network (CNN) based denoiser and a nonlo…

DenoisingImage Denoising

Exploiting sparsity to build efficient kernel based collaborative filtering for top-N item recommendation

2016-12-17 · Mirko Polato, Fabio Aiolli

The increasing availability of implicit feedback datasets has raised the interest in developing effective collaborative filtering techniques able to deal asymmetrically with unambiguous positive feedback and ambiguous ne…

Collaborative Filtering

Network Pruning via Annealing and Direct Sparsity Control

2020-02-11 · Yangzi Guo, Yiyuan She, Adrian Barbu

Artificial neural networks (ANNs) especially deep convolutional networks are very popular these days and have been proved to successfully offer quite reliable solutions to many vision problems. However, the use of deep n…

Network Pruning