Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers

Benchmark Model Rank Results
facial-expression-recognition-on-affectnetViT-base–Accuracy (8 emotion): 57.99
facial-expression-recognition-on-affectnetViT-tiny–Accuracy (8 emotion): 58.28
facial-expression-recognition-on-affectnetVit-base + MAE–Accuracy (8 emotion): 62.42
facial-expression-recognition-on-fer-plusViT-base–Accuracy: 88.91
facial-expression-recognition-on-fer-plusViT-tiny–Accuracy: 88.56
facial-expression-recognition-on-fer-plusVit-base + MAE–Accuracy: 90.18
facial-expression-recognition-on-raf-dbViT-base–Overall Accuracy: 87.22
facial-expression-recognition-on-raf-dbViT-base + MAE–Overall Accuracy: 91.07
facial-expression-recognition-on-raf-dbViT-tiny–Overall Accuracy: 87.03