From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search
share
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 (an improvement of 2.5 our model, NEXcepTion-TP, reaches 81.8 (82.1 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.
READ FULL TEXT