ThreshNet: 一种高效的DenseNet,利用阈值机制减少连接
ThreshNet: An Efficient DenseNet Using Threshold Mechanism to Reduce Connections
AI总结:
ThreshNet通过阈值机制优化连接方法,提升推理速度并减少参数量,适用于移动设备。
摘要:
随着神经网络在计算机视觉任务中的不断发展,越来越多的网络架构取得了显著的成功。作为最先进的神经网络架构之一,DenseNet通过将所有特征图连接起来以解决模型深度问题。尽管这种网络架构在参数较少的情况下具有优异的精度,但其推理时间却过于冗长。为了解决这个问题,HarDNet减少了特征图之间的连接,使剩余的连接呈现出类似正弦波的形状。然而,这种压缩方法可能导致模型精度的降低以及参数和模型大小的增加。这种网络架构可能会减少内存访问时间,但其整体性能仍可进一步提升。因此,我们提出了一种新的网络架构ThreshNet,利用阈值机制进一步优化连接方法。不同卷积层的不同连接数被丢弃以加快网络的推理速度。所提出的网络在NVIDIA RTX 3050和Raspberry Pi 4平台上使用CIFAR 10和SVHN数据集进行评估。实验结果表明,与HarDNet68、GhostNet、MobileNetV2、ShuffleNet和EfficientNet相比,所提出的ThreshNet79的推理时间分别快了5%、9%、10%、18%和20%。ThreshNet95的参数数量比HarDNet85少55%。新的模型压缩和模型加速方法可以加快推理时间,使网络模型能够在移动设备上运行。
英文摘要:
With the continuous development of neural networks for computer vision tasks, more and more network architectures have achieved outstanding success. As one of the most advanced neural network architectures, DenseNet shortcuts all feature maps to solve the model depth problem. Although this network architecture has excellent accuracy with low parameters, it requires an excessive inference time. To solve this problem, HarDNet reduces the connections between the feature maps, making the remaining connections resemble harmonic waves. However, this compression method may result in a decrease in the model accuracy and an increase in the parameters and model size. This network architecture may reduce the memory access time, but its overall performance can still be improved. Therefore, we propose a new network architecture, ThreshNet, using a threshold mechanism to further optimize the connection method. Different numbers of connections for different convolution layers are discarded to accelerate the inference of the network. The proposed network has been evaluated with image classification using CIFAR 10 and SVHN datasets under platforms of NVIDIA RTX 3050 and Raspberry Pi 4. The experimental results show that, compared with HarDNet68, GhostNet, MobileNetV2, ShuffleNet, and EfficientNet, the inference time of the proposed ThreshNet79 is 5%, 9%, 10%, 18%, and 20% faster, respectively. The number of parameters of ThreshNet95 is 55% less than that of HarDNet85. The new model compression and model acceleration methods can speed up the inference time, enabling network models to operate on mobile devices.
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。