In this paper, we present a modified Xception architecture, the NEXcepTion network. Our network has significantly better performance than the original Xception, achieving top-1 accuracy of 81.5% on the ImageNet validation dataset (an improvement of 2.5%) as well as a 28% higher throughput. Another variant of our model, NEXcepTion-TP, reaches 81.8% top-1 accuracy, similar to ConvNeXt (82.1%), while having a 27% higher throughput. Our model is the result of applying improved training procedures and new design decisions combined with an application of Neural Architecture Search (NAS) on a smaller dataset. These findings call for revisiting older architectures and reassessing their potential when combined with the latest enhancements.
翻译：在本文中,我们提出了一个修改的 Xception 架构, 即 NEXcepTion 网络。 我们的网络比原 Xcepion 的功能要好得多, 在图像网络验证数据集( 改善2.5% ) 上方-1 精确度达到 8. 5%, 以及 28% 的输送量更高 。 我们的模型的另一个变种, 即 NEXcepTion-TP, 达到81.8% 的顶端-1 精确度, 类似于 ConvNeXt ( 82.1%), 并拥有27% 的通过量。 我们的模型是应用改进的培训程序和新的设计决定, 加上将神经结构搜索( NAS NAS) 应用于一个较小的数据集的结果。 这些发现要求重新审视旧的架构, 并在与最新的增强相结合时重新评估其潜力 。
相关内容
微信扫码咨询专知VIP会员