论文标题
从X敏感到联系：新的设计决策和神经体系结构搜索
From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search
论文作者
论文摘要
在本文中，我们提出了一个修改后的Xpection体系结构，即Nexception网络。我们的网络的性能明显优于原始Xception，在ImageNet验证数据集（提高2.5％）上的TOP-1精度为81.5％，并且吞吐量高28％。我们模型的另一个变体Nexception-TP达到了81.8％的TOP-1准确性，类似于Convnext（82.1％），而吞吐量则高27％。我们的模型是应用改进的培训程序和新的设计决策的结果，并在较小的数据集中应用神经体系结构搜索（NAS）的应用。这些发现要求重新审视较旧的体系结构，并在结合最新增强功能时重新评估其潜力。
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.
