A Lightweight Binarized Convolutional Neural Network Model for Small Memory and Low-Cost Mobile Devices

Table 1

The accuracy performance of different methods is compared on the GTSRB dataset.

Methods	Accuracy (%)	Params (M)
HOG + SVM [42]	77.6	—
LBP + SVM [42]	71.1	—
LBP + RF [42]	69.7	—
PI + LDA + SVM [42]	82.3	—
LDA + RF [42]	82.3	—
Faster R-CNN [41]	91.8	—
Multiscale CNN [36]	95.4	—
MobileNet [39]	88.15	—
ShuffleNet [39]	88.99	—
EffNet [39]	91.79	—
Multicolumn [37]	99.46	90
Weighted multiconvolutional [38]	99.59	75.3
DCR (bitwise operation) [40]	92.86	0.83
CBCNN (ours, bitwise operation)	92.94	0.59