Learning Filter Basis for Convolutional Neural Network Compression
Convolutional neural networks (CNNs) based solutions have achieved state-of-the-art performances for many computer vision tasks, including classification and super-resolution of images. Usually the success of these methods comes with a cost of millions of parameters due to stacking deep convolutional layers. Moreover, quite a large number of filters are also used for a single convolutional layer, which exaggerates the parameter burden of current methods. Thus, in this paper, we try to reduce the number of parameters of CNNs by learning a basis of the filters in convolutional layers. For the forward pass, the learned basis is used to approximate the original filters and then used as parameters for the convolutional layers. We validate our proposed solution for multiple CNN architectures on image classification and image super-resolution benchmarks and compare favorably to the existing state-of-the-art in terms of reduction of parameters and preservation of accuracy.
Code (3)
Tasks
General Classificationimage-classificationImage ClassificationImage Super-ResolutionNeural Network CompressionSuper-ResolutionSimilar Papers 제목 키워드 기반
Compressing Deep CNNs using Basis Representation and Spectral Fine-tuning
We propose an efficient and straightforward method for compressing deep convolutional neural networks (CNNs) that uses basis filters to represent the convolutional layers, and optimizes the performance of the compressed …
image-classificationImage Classificationobject-detectionObject DetectionDCT-Conv: Coding filters in convolutional networks with Discrete Cosine Transform
Convolutional neural networks are based on a huge number of trained weights. Consequently, they are often data-greedy, sensitive to overtraining, and learn slowly. We follow the line of research in which filters of convo…
FSNet: Compression of Deep Convolutional Neural Networks by Filter Summary
We present a novel method of compression of deep Convolutional Neural Networks (CNNs) by weight sharing through a new representation of convolutional filters. The proposed method reduces the number of parameters of each …
General Classificationimage-classificationImage ClassificationNeural Architecture Search+3Structural Compression of Convolutional Neural Networks
Deep convolutional neural networks (CNNs) have been successful in many tasks in machine vision, however, millions of weights in the form of thousands of convolutional filters in CNNs makes them difficult for human intepr…
DiversityGeneral ClassificationA pruning method based on the dissimilarity of angle among channels and filters
Convolutional Neural Network (CNN) is more and more widely used in various fileds, and its computation and memory-demand are also increasing significantly. In order to make it applicable to limited conditions such as emb…
Network Pruning