Cell Classification on C-NMC 2019 (test)
97.89F1 ScoreProposed model
Evaluation Results
| Method | Links | |
|---|---|---|
| Proposed modelApproach=EfficientNetV2-B3 + SE attention2026.01 | 97.89 | |
| Sampathila et al.Approach=Custom CNN with augmentation2026.01 | 95.43 | |
| Talaat and GamelApproach=CNN with hyperparameter optimization2026.01 | 94.07 | |
| Sant’Anna et al.Approach=Feature extraction + ensemble (ANN+SVM+NB)2026.01 | 93.7 | |
| Oliveira and DantasApproach=VGG16 with augmentation2026.01 | 92.6 | |
| Pan et al.Approach=Transfer learning ResNets + correction2026.01 | 92.5 | |
| Honnalgere and NayakApproach=Transfer learning VGG162026.01 | 91.7 | |
| Xiao et al.Approach=Multi-model ensemble2026.01 | 90.3 | |
| Verma and SinghApproach=Transfer learning MobileNetV22026.01 | 89.47 | |
| Prellberg and KramerApproach=ResNeXt50 from scratch2026.01 | 87.89 | |
| Shah et al.Approach=Transfer learning CNN-RNN2026.01 | 87.58 | |
| Marzahl et al.Approach=Transfer learning ResNet182026.01 | 87.46 | |
| Ding et al.Approach=InceptionV3, DenseNet, InceptionResNetV22026.01 | 86.74 | |
| Kulhalli et al.Approach=ResNeXt50 and ResNeXt1012026.01 | 85.7 | |
| Liu and LongApproach=Transfer learning Inception + ResNets2026.01 | 84 | |
| Khan and ChooApproach=Transfer learning ResNets + SENets2026.01 | 81.79 |