Thispaper presents anefficient multi-scale vision Transformer,called ResT,that capably served as a general-purpose backbone for image recognition.

Theoretical and empirical studies [21,77,9,55,49,5,12]postulate that such flatter regions generalize better than sharper minima, e.g., due to the flat minimizer's robustness against loss function shifts between trainandtestdata,asillustrated inFig.1.

However, the model size and corresponding computational complexity are constantly scaled up in pursuit of higher performance.