...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Image and Vision Computing >FALF ConvNets: Fatuous auxiliary loss based filter-pruning for efficient deep CNNs
【24h】

FALF ConvNets: Fatuous auxiliary loss based filter-pruning for efficient deep CNNs

机译：FALF ConvNets：基于致命辅助损失的滤波器修剪，可实现高效的深层CNN

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Obtaining efficient Convolutional Neural Networks (CNNs) are imperative to enable their application for a wide variety of tasks (classification, detection, etc.). While several methods have been proposed to solve this problem, we propose a novel strategy for solving the same that is orthogonal to the strategies proposed so far. We hypothesize that if we add a fatuous auxiliary task, to a network which aims to solve a semantic task such as classification or detection, the filters devoted to solving this frivolous task would not be relevant for solving the main task of concern. These filters could be pruned and pruning these would not reduce the performance on the original task. We demonstrate that this strategy is not only successful, it in fact allows for improved performance for a variety of tasks such as object classification, detection and action recognition. An interesting observation is that the task needs to be fatuous so that any semantically meaningful filters would not be relevant for solving this task. We thoroughly evaluate our proposed approach on different architectures (LeNet, VGG-16, ResNet, Faster RCNN, SSD-512, C3D, and MobileNet V2) and datasets (MNIST, CIFAR, ImageNet, GTSDB, COCO, and UCF101) and demonstrate its generalizability through extensive experiments. Moreover, our compressed models can be used at run-time without requiring any special libraries or hardware. Our model compression method reduces the number of FLOPS by an impressive factor of 6.03X and GPU memory footprint by more than 17X for VGG-16, significantly outperforming other state-of-the-art filter pruning methods. We demonstrate the usability of our approach for 3D convolutions and various vision tasks such as object classification, object detection, and action recognition. (C) 2019 Elsevier B.V. All rights reserved.
机译：获得有效的卷积神经网络（CNN）势在必行，以使其能够用于多种任务（分类，检测等）。虽然已经提出了几种方法来解决此问题，但我们提出了一种新颖的解决方案，该策略与迄今为止提出的策略正交。我们假设，如果我们向旨在解决诸如分类或检测之类的语义任务的网络添加一个繁琐的辅助任务，那么专门用于解决这一琐碎任务的过滤器将与解决所关注的主要任务无关。可以修剪这些过滤器，并且修剪这些过滤器不会降低原始任务的性能。我们证明了该策略不仅成功，而且实际上可以提高各种任务的性能，例如对象分类，检测和动作识别。一个有趣的观察是，任务必须是繁重的，以便任何语义上有意义的过滤器都不会与解决此任务相关。我们对不同架构（LeNet，VGG-16，ResNet，Faster RCNN，SSD-512，C3D和MobileNet V2）和数据集（MNIST，CIFAR，ImageNet，GTSDB，COCO和UCF101）进行了彻底评估，并对其进行了验证。通过广泛的实验来推广。此外，我们的压缩模​​型可以在运行时使用，而无需任何特殊的库或硬件。对于VGG-16，我们的模型压缩方法将FLOPS的数量减少了6.03倍，而GPU内存占用量则减少了17倍以上，大大超过了其他最新的过滤器修剪方法。我们证明了我们的方法可用于3D卷积和各种视觉任务（例如对象分类，对象检测和动作识别）的可用性。 （C）2019 Elsevier B.V.保留所有权利。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号