New Pruning Method Based on DenseNet Network for Image Classification
Deep neural networks have made significant progress in the field of computer vision. Recent studies have shown that depth, width and shortcut connections of neural network architectures play a crucial role in their performance. One of the most advanced neural network architectures, DenseNet, has achieved excellent convergence rates through dense connections. However, it still has obvious shortcomings in the usage of amount of memory. In this paper, we introduce a new type of pruning tool, threshold, which refers to the principle of the threshold voltage in MOSFET. This work employs this method to connect blocks of different depths in different ways to reduce the usage of memory. It is denoted as ThresholdNet. We evaluate ThresholdNet and other different networks on datasets of CIFAR10. Experiments show that HarDNet is twice as fast as DenseNet, and on this basis, ThresholdNet is 10% faster and 10% lower error rate than HarDNet.
Code (0)
등록된 구현이 없습니다.
Tasks
Classificationimage-classificationImage ClassificationNetwork PruningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Learning to Search Efficient DenseNet with Layer-wise Pruning
Deep neural networks have achieved outstanding performance in many real-world applications with the expense of huge computational resources. The DenseNet, one of the recently proposed neural network architecture, has ach…
Reinforcement LearningEvolving Character-Level DenseNet Architectures using Genetic Programming
DenseNet architectures have demonstrated impressive performance in image classification tasks, but limited research has been conducted on using character-level DenseNet (char-DenseNet) architectures for text classificati…
ClassificationGeneral Classificationimage-classificationImage Classification+2Channel Pruning via Multi-Criteria based on Weight Dependency
Channel pruning has demonstrated its effectiveness in compressing ConvNets. In many related arts, the importance of an output feature map is only determined by its associated filter. However, these methods ignore a small…
image-classificationImage ClassificationDense xUnit Networks
Deep net architectures have constantly evolved over the past few years, leading to significant advancements in a wide array of computer vision tasks. However, besides high accuracy, many applications also require a low c…
DenoisingImage RestorationSuper-ResolutionDenseNet approach to segmentation and classification of dermatoscopic skin lesions images
At present, cancer is one of the most important health issues in the world. Because early detection and appropriate treatment in cancer are very effective in the recovery and survival of patients, image processing as a d…
ClassificationDiagnosticimage-classificationImage Classification+3