From Xception to NEXcepTion: New Design Decisions and Neural Architecture Search
This work addresses performance bottlenecks in computer vision models for researchers and practitioners, but it is incremental as it builds on an existing architecture with modern enhancements.
The authors tackled improving the Xception architecture by introducing NEXcepTion, achieving a top-1 accuracy of 81.5% on ImageNet (a 2.5% improvement) and 28% higher throughput, with a variant reaching 81.8% accuracy and 27% higher throughput.
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.