arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2104.13993cs.CV
收藏

用于图像分类任务的卷积网络滤波器分布模板

Filter Distribution Templates in Convolutional Networks for Image Classification Tasks

University of Bristol(布里斯托大学)

Ramon Izquierdo-Cordova, Walterio Mayol-Cuevas

摘要:

神经网络设计者通过增加模型深度、引入新的层类型和发现新的层组合来实现渐进的准确性。许多架构中的一个共同元素是每层中过滤器数量的分布。神经网络模型在更深层保持增加过滤器的模式设计,例如LeNet,VGG,ResNet,MobileNet甚至自动发现架构(如NASNet)中的过滤器。它仍然是未知的,如果过滤器的这种金字塔分布是最好的不同的任务和约束。在这项工作中,我们提出了一系列的修改,在四个流行的神经网络模型中的过滤器的分布和它们的影响,在准确性和资源消耗。结果表明,通过应用这种方法,一些模型的精度提高了8.9%,参数减少了54%。

英文摘要:

Neural network designers have reached progressive accuracy by increasing models depth, introducing new layer types and discovering new combinations of layers. A common element in many architectures is the distribution of the number of filters in each layer. Neural network models keep a pattern design of increasing filters in deeper layers such as those in LeNet, VGG, ResNet, MobileNet and even in automatic discovered architectures such as NASNet. It remains unknown if this pyramidal distribution of filters is the best for different tasks and constrains. In this work we present a series of modifications in the distribution of filters in four popular neural network models and their effects in accuracy and resource consumption. Results show that by applying this approach, some models improve up to 8.9% in accuracy showing reductions in parameters up to 54%.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑