paper-with-me

홈 › Papers

Learning to Prune Filters in Convolutional Neural Networks

2018-01-23 · Qiangui Huang, Kevin Zhou, Suya You, Ulrich Neumann

Many state-of-the-art computer vision algorithms use large scale convolutional neural networks (CNNs) as basic building blocks. These CNNs are known for their huge number of parameters, high redundancy in weights, and tremendous computing resource consumptions. This paper presents a learning algorithm to simplify and speed up these CNNs. Specifically, we introduce a "try-and-learn" algorithm to train pruning agents that remove unnecessary CNN filters in a data-driven way. With the help of a novel reward function, our agents removes a significant number of filters in CNNs while maintaining performance at a desired level. Moreover, this method provides an easy control of the tradeoff between network performance and its scale. Per- formance of our algorithm is validated with comprehensive pruning experiments on several popular CNNs for visual recognition and semantic segmentation tasks.

📄 PDF Abstract BibTeX arXiv:1801.07365

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic Segmentation

Methods 이 논문이 사용한 방법론

Pruning 설명 없음
SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Asymptotic Soft Filter Pruning for Deep Convolutional Neural Networks

2018-08-22 · Yang He, Xuanyi Dong, Guoliang Kang, Yanwei Fu 외

Deeper and wider Convolutional Neural Networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such over-parameterized neural network has received increased attention. A typical pru…

image-classificationImage Classification

Reconstructing Pruned Filters using Cheap Spatial Transformations

2021-10-25 · Roy Miles, Krystian Mikolajczyk

We present an efficient alternative to the convolutional layer using cheap spatial transformations. This construction exploits an inherent spatial redundancy of the learned convolutional filters to enable a much greater …

Feature CompressionKnowledge DistillationModel Compression

Interpreting Convolutional Neural Networks Through Compression

2017-11-07 · Reza Abbasi-Asl, Bin Yu

Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of par…

Object Recognition

Studying the Plasticity in Deep Convolutional Neural Networks using Random Pruning

2018-12-26 · Deepak Mittal, Shweta Bhardwaj, Mitesh M. Khapra, Balaraman Ravindran

Recently there has been a lot of work on pruning filters from deep convolutional neural networks (CNNs) with the intention of reducing computations.The key idea is to rank the filters based on a certain criterion (say, l…

image-classificationImage ClassificationImage Segmentationobject-detection+2

Semantic Pruning for Single Class Interpretability

2019-09-25 · Kamila Abdiyeva, Martin Lukac, Kanat Alimanov

Convolutional Neural Networks (CNN) have achieved state-of-the-art performance in different computer vision tasks, but at a price of being computationally and power intensive. At the same time, only a few attempts were m…

Classification