Research Article
Model Lightweighting for Real-time Distraction Detection on Resource-Limited Devices
Table 5
Comparisons with the state-of- the-art methods in the literature for the StateFarm dataset with the dataset randomly split by 7 : 3.
| Model | Top-1 acc (%) | Params (M) |
| InceptionV3 [22] | 92.90 | 25.6 | Xception [22] | 82.50 | 22.9 | InceptionV3 + Xception [22] | 90.00 | 46.7 | InceptionV3 + Xception + ResNet50 + VGG-19 [22] | 97.00 | 214.3 | D-HCNN [31] | 99.82 | 0.76 | MobileNetV2 | 99.57 | 3.5 | MobileNetV2-tiny | 99.88 | 2.78 |
|
|