From: High-throughput soybean seeds phenotyping with convolutional neural networks and transfer learning
Dataset | Small dataset in the image size of 256 × 256 | |||||||
---|---|---|---|---|---|---|---|---|
Pre-trained model | Pre-trained COCO weights [35] | |||||||
Backbone layer | ResNet50-FPN | ResNet101-FPN | ||||||
Test dataset | Synthetic | Real-world | Synthetic | Real-world | ||||
256 | 512 | 1024 | 256 | 512 | 1024 | |||
Recall50 | 0.75 | 0.84 | 0.79 | 0.45 | 0.88 | 0.65 | 0.57 | 0.91 |
AP50 | 0.76 | 0.85 | 0.82 | 0.54 | 0.92 | 0.65 | 0.62 | 0.91 |
AP75 | 0.76 | 0.58 | 0.40 | 0.11 | 0.92 | 0.64 | 0.62 | 0.89 |
AP@[0.5:0.95] | 0.67 | 0.51 | 0.43 | 0.22 | 0.80 | 0.50 | 0.47 | 0.66 |