Change Detection On Whu Cd
Metrics
F1
IoU
Overall Accuracy
Precision
Recall
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | F1 | IoU | Overall Accuracy | Precision | Recall |
|---|---|---|---|---|---|
| rethinking-remote-sensing-change-detection | 91.56 | 84.44 | 99.23 | 92.25 | 90.89 |
| ddlnet-boosting-remote-sensing-change | 90.56 | 82.75 | 99.13 | 91.56 | 90.03 |
| tinycd-a-not-so-deep-learning-model-for | 91.05 | 83.57 | 99.10 | 92.68 | 89.47 |
| hanet-a-hierarchical-attention-network-for | 88.16 | 78.82 | 99.16 | 88.30 | 88.01 |
| lrnet-change-detection-of-high-resolution | 92.51 | 86.06 | 99.47 | 95.11 | 90.04 |
| change-guiding-network-incorporating-change | 92.59 | 86.21 | 99.48 | 94.47 | 90.79 |
| rs-mamba-for-large-remote-sensing-image-dense | 91.87 | 84.96 | - | 93.37 | 90.42 |
| t-unet-triplet-unet-for-change-detection-in | 91.77 | - | 99.42 | 95.44 | 88.37 |
| lwganet-a-lightweight-group-attention | 95.24 | 90.92 | - | 96.51 | - |
| bifa-remote-sensing-image-change-detection | 94.37 | 89.34 | 99.56 | 95.15 | 93.60 |
| building-change-detection-for-remote-sensing | 89.75 | 81.40 | - | 90.15 | 89.35 |
| remote-sensing-change-detection-segmentation | 92.65 | - | 99.42 | - | - |
| changemamba-remote-sensing-change-detection | 94.19 | 89.02 | 99.58 | 96.18 | 92.23 |
| dsfer-net-a-deep-supervision-and-feature | 92.58 | 86.18 | 99.46 | 94.17 | 91.04 |
| c2f-semicd-a-coarse-to-fine-semi-supervised | 94.36 | 89.33 | 99.56 | 96.57 | 92.26 |
| stnet-spatial-and-temporal-feature-fusion | 87.46 | 77.72 | 98.85 | 87.84 | 87.08 |
| hcgmnet-a-hierarchical-change-guiding-map | 92.08 | 85.33 | 99.45 | 93.93 | 90.31 |
| src-net-bi-temporal-spatial-relationship | 92.06 | 85.28 | 99.30 | 92.57 | 91.55 |
| rfl-cdnet-towards-accurate-change-detection | 91.39 | - | - | 91.33 | 91.46 |
| cdmamba-remote-sensing-image-change-detection | 93.76 | 88.26 | 99.51 | 95.58 | 92.01 |