• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Artificial Neural Networks >Dynamically Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence
【24h】

Dynamically Sacrificing Accuracy for Reduced Computation: Cascaded Inference Based on Softmax Confidence

机译：动态牺牲精度以减少计算量：基于Softmax置信度的级联推理

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

We study the tradeoff between computational effort and classification accuracy in a cascade of deep neural networks. During inference, the user sets the acceptable accuracy degradation which then automatically determines confidence thresholds for the intermediate classifiers. As soon as the confidence threshold is met, inference terminates immediately without having to compute the output of the complete network. Confidence levels are derived directly from the softmax outputs of intermediate classifiers, as we do not train special decision functions. We show that using a softmax output as a confidence measure in a cascade of deep neural networks leads to a reduction of 15%-50% in the number of MAC operations while degrading the classification accuracy by roughly 1%. Our method can be easily incorporated into pre-trained non-cascaded architectures, as we exemplify on ResNet. Our main contribution is a method that dynamically adjusts the tradeoff between accuracy and computation without retraining the model.
机译：我们在级联的深度神经网络中研究了计算工作量和分类准确性之间的权衡。在推断过程中，用户设置可接受的精度下降，然后自动确定中间分类器的置信度阈值。一旦满足置信度阈值，推理便会立即终止，而无需计算整个网络的输出。由于我们不训练特殊决策函数，因此置信度直接来自中间分类器的softmax输出。我们证明了在深度神经网络的级联中使用softmax输出作为置信度度量会导致MAC运算数量减少15％-50％，同时将分类精度降低大约1％。正如我们在ResNet上所举例说明的那样，我们的方法可以很容易地并入预训练的非级联体系结构中。我们的主要贡献是一种无需调整模型即可动态调整精度与计算之间折衷的方法。

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