Expression Recognition on FER 2013
95.6AccuracySyed
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SyedModel=Mini Xception2026.05 | 95.6 | — | |
| GiannopoulosModel=CNN2026.05 | 83 | — | |
| MT-ArcResLoss Function=ArcFace, Training=Re-trained2019.09 | 80 | — | |
| MT-ArcVGGLoss Function=ArcFace, Training=Re-trained2019.09 | 79 | — | |
| FT-MT-VGGBackbone=MT-VGG, Training=Fine-tuned2019.09 | 78 | — | |
| MT-VGGTraining=Trained on Aff-Wild22019.09 | 76 | — | |
| VGG2019.09 | 75 | — | |
| KhaireddinModel=CNN2026.05 | 73.28 | — | |
| JaiswalModel=CNN2026.05 | 70.14 | — | |
| xCLIPBackbone=ViT-B/16, Pre-trained on=IT35M, Mode=Zero-shot2022.10 | 39 | — | |
| CLIPBackbone=ViT-B/16, Pre-trained on=IT35M, Mode=Zero-shot2022.10 | 37.3 | — | |
| nCLIPBackbone=ViT-B/16, Pre-trained on=IT35M, Mode=Zero-shot2022.10 | 13.5 | — | |
| CLIPevaluation=linear probing2022.08 | — | 72.9 | |
| CLIPPre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.03 | — | 39.9 | |
| FLAIRBackbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.03 | — | 30.6 | |
| ITOPre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.03 | — | 37.8 | |
| ITO sub2Backbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.03 | — | 22.4 | |
| ITO sub2Pre-training Dataset=DataComp-1B, Backbone=ViT-B/16, Training Epochs=10 epochs, Zero-shot protocol=EVA-CLIP2026.03 | — | 32.4 | |
| ITO sub3Backbone=ViT-B/16, Pre-training Dataset=CC3M-recap, Evaluation Protocol=Zero-shot2026.03 | — | 19.6 | |
| LOUPEevaluation=linear probing2022.08 | — | 70.7 |