Research Article

Robustness and Explainability of Image Classification Based on QCNN

Table 1

Experimental results of different bitplanes on MERA and boxcounting features.

FeatureMERA accuracyBox accuracyMERA lossBox loss

Original0.95310.98440.25260.0837
Bitplane10.72460.73260.23530.3046
Bitplane20.72440.73550.28390.2101
Bitplane30.72030.73640.28920.2299
Bitplane40.73480.75520.24860.2869
Bitplane50.96880.89060.21180.7642
Bitplane60.98440.90620.20440.2981
Bitplane70.98440.82810.61440.7873
Bitplane80.95310.98210.75350.6259