Facial Expression Recognition On Fer2013

Metrics

Accuracy

Results

Performance results of various models on this benchmark

		Paper Title
Regularized Xception with Step Decay Learning	94.34	Regularized Xception for facial expression recognition with extra training data and step decay learning rate
ResEmoteNet	79.79	ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition
Ensemble ResMaskingNet with 6 other CNNs	76.82	Facial Expression Recognition using Residual Masking Network
Mini-ResEmoteNet (A)	76.33	Mini-ResEmoteNet: Leveraging Knowledge Distillation for Human-Centered Design
EmoNeXt	76.12	EmoNeXt: an Adapted ConvNeXt for Facial Emotion Recognition
Segmentation VGG-19	75.97	A novel facial emotion recognition model using segmentation VGG-19 architecture
Local Learning Deep+BOW	75.42	Local Learning with Deep and Handcrafted Features for Facial Expression Recognition
LHC-Net	74.42	Local Multi-Head Channel Self-Attention for Facial Expression Recognition
Residual Masking Network	74.14	Facial Expression Recognition using Residual Masking Network
ResNet18 With Tricks	73.70	Fer2013 Recognition - ResNet18 With Tricks
VGGNet	73.28	Facial Emotion Recognition: State of the Art Performance on FER2013
CNN Hyperparameter Optimisation	72.16	Convolutional Neural Network Hyperparameters optimization for Facial Emotion Recognition
Ad-Corre	72.03	Ad-Corre: Adaptive Correlation-Based Loss for Facial Expression Recognition in the Wild
Mini-ResEmoteNet (B)	70.20	Mini-ResEmoteNet: Leveraging Knowledge Distillation for Human-Centered Design
DeepEmotion	70.02	Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network
Local Learning BOW	67.48	Challenges in Representation Learning: A report on three machine learning contests

0 of 16 row(s) selected.

Facial Expression Recognition On Fer2013 | SOTA | HyperAI