Facial Expression Recognition (FER) on RAF-DB

Metric: Overall Accuracy (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	Overall Accuracy▼	Extra Data	Paper	Date↕	Code
1	ResEmoteNet	94.76	Yes	ResEmoteNet: Bridging Accuracy and Loss Reductio...	2024-09-01	Code
2	FMAE	93.45	Yes	Representation Learning and Identity Adversarial...	2024-07-15	Code
3	QCS	93.02	No	QCS: Feature Refining from Quadruplet Cross Simi...	2024-11-04	Code
4	Norface	92.97	No	Norface: Improving Facial Expression Analysis by...	2024-07-22	Code
5	S2D	92.57	No	From Static to Dynamic: Adapting Landmark-Aware ...	2023-12-09	Code
6	BTN	92.54	No	Batch Transformer: Look for Attention in Batch	2024-07-05	-
7	GReFEL	92.47	No	GReFEL: Geometry-Aware Reliable Facial Expressio...	2024-10-21	-
8	DDAMFN++	92.34	Yes	-	-	Code
9	DCJT	92.24	Yes	-	-	Code
10	POSTER++	92.21	No	POSTER++: A simpler and stronger facial expressi...	2023-01-28	Code
11	APViT	91.98	No	Vision Transformer with Attentive Pooling for Ro...	2022-12-11	Code
12	DDAMFN	91.35	No	-	-	Code
13	ViT-base + MAE	91.07	No	Emotion Separation and Recognition from a Facial...	2022-07-22	-
14	LFNSB	91.07	No	-	-	Code
15	ExpLLM	91.03	No	ExpLLM: Towards Chain of Thought for Facial Expr...	2024-09-04	Code
16	EAC(ResNet-50)	90.35	No	Learn From All: Erasing Attention Consistency fo...	2022-07-21	Code
17	Ada-DF	90.04	No	-	-	Code
18	DAN	89.7	No	Distract Your Attention: Multi-head Cross Attent...	2021-09-15	Code
19	RUL (ResNet-18)	88.98	No	-	-	Code
20	PSR	88.98	Yes	-	-	Code
21	FerNeXt	88.56	No	-	-	Code
22	EfficientFace	88.36	No	-	-	Code
23	MA-Net	88.36	No	-	-	Code
24	DACL (ResNet-18)	87.78	Yes	-	-	Code
25	MixAugment	87.54	No	MixAugment & Mixup: Augmentation Methods for Fac...	2022-05-09	-
26	ViT-base	87.22	No	Emotion Separation and Recognition from a Facial...	2022-07-22	-
27	ViT-tiny	87.03	No	Emotion Separation and Recognition from a Facial...	2022-07-22	-
28	Ad-Corre	86.96	No	-	-	Code
29	RAN (ResNet-18)	86.9	Yes	Region Attention Networks for Pose and Occlusion...	2019-05-10	Code

#1ResEmoteNetSOTA
94.76
Overall Accuracy· Extra Data· 2024-09-01
ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition Code
#2FMAESOTA
93.45
Overall Accuracy· Extra Data· 2024-07-15
Representation Learning and Identity Adversarial Training for Facial Behavior Understanding Code
#3QCS
93.02
Overall Accuracy· 2024-11-04
QCS: Feature Refining from Quadruplet Cross Similarity for Facial Expression Recognition Code
#4Norface
92.97
Overall Accuracy· 2024-07-22
Norface: Improving Facial Expression Analysis by Identity Normalization Code
#5S2DSOTA
92.57
Overall Accuracy· 2023-12-09
From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos Code
#6BTN
92.54
Overall Accuracy· 2024-07-05
Batch Transformer: Look for Attention in Batch
#7GReFEL
92.47
Overall Accuracy· 2024-10-21
GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution
#8DDAMFN++
92.34
Overall Accuracy· Extra Data
No paperCode
#9DCJT
92.24
Overall Accuracy· Extra Data
No paperCode
#10POSTER++SOTA
92.21
Overall Accuracy· 2023-01-28
POSTER++: A simpler and stronger facial expression recognition network Code
#11APViTSOTA
91.98
Overall Accuracy· 2022-12-11
Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition Code
#12DDAMFN
91.35
Overall Accuracy
No paperCode
#13ViT-base + MAESOTA
91.07
Overall Accuracy· 2022-07-22
Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers
#14LFNSB
91.07
Overall Accuracy
No paperCode
#15ExpLLM
91.03
Overall Accuracy· 2024-09-04
ExpLLM: Towards Chain of Thought for Facial Expression Recognition Code
#16EAC(ResNet-50)SOTA
90.35
Overall Accuracy· 2022-07-21
Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition Code
#17Ada-DF
90.04
Overall Accuracy
No paperCode
#18DANSOTA
89.7
Overall Accuracy· 2021-09-15
Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition Code
#19RUL (ResNet-18)
88.98
Overall Accuracy
No paperCode
#20PSR
88.98
Overall Accuracy· Extra Data
No paperCode
#21FerNeXt
88.56
Overall Accuracy
No paperCode
#22EfficientFace
88.36
Overall Accuracy
No paperCode
#23MA-Net
88.36
Overall Accuracy
No paperCode
#24DACL (ResNet-18)
87.78
Overall Accuracy· Extra Data
No paperCode
#25MixAugment
87.54
Overall Accuracy· 2022-05-09
MixAugment & Mixup: Augmentation Methods for Facial Expression Recognition
#26ViT-base
87.22
Overall Accuracy· 2022-07-22
Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers
#27ViT-tiny
87.03
Overall Accuracy· 2022-07-22
Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers
#28Ad-Corre
86.96
Overall Accuracy
No paperCode
#29RAN (ResNet-18)SOTA
86.9
Overall Accuracy· Extra Data· 2019-05-10
Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition Code