Papers › Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation

Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation

13 May 2021arXiv:2105.06421archive 2025-07-28

Mahdi Pourmirzaei, Gholam Ali Montazer, Farzaneh Esmaili

In this paper, at first, the impact of ImageNet pre-training on fine-grained Facial Emotion Recognition (FER) is investigated which shows that when enough augmentations on images are applied, training from scratch provides better result than fine-tuning on ImageNet pre-training. Next, we propose a method to improve fine-grained and in-the-wild FER, called Hybrid Multi-Task Learning (HMTL). HMTL uses Self-Supervised Learning (SSL) as an auxiliary task during classical Supervised Learning (SL) in the form of Multi-Task Learning (MTL). Leveraging SSL during training can gain additional information from images for the primary fine-grained SL task. We investigate how proposed HMTL can be used in the FER domain by designing two customized version of common pre-text task techniques, puzzling and in-painting. We achieve state-of-the-art results on the AffectNet benchmark via two types of HMTL, without utilizing pre-training on additional data. Experimental results on the common SSL pre-training and proposed HMTL demonstrate the difference and superiority of our work. However, HMTL is not only limited to FER domain. Experiments on two types of fine-grained facial tasks, i.e., head pose estimation and gender recognition, reveals the potential of using HMTL to improve fine-grained facial representation.

PaperPDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Emotion RecognitionFacial Emotion RecognitionFacial Expression Recognition (FER)Head Pose EstimationMulti-Task LearningPose EstimationSelf-Supervised Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Facial Expression Recognition (FER) AffectNet SL + SSL in-panting-pl (B0) Accuracy (8 emotion) 61.72 #17 of 50 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet SL + SSL puzzling (B2) Accuracy (8 emotion) 61.32 #20 of 50 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet SL + SSL puzzling (B0) Accuracy (8 emotion) 61.09 #21 of 50 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet SL (B2) Accuracy (8 emotion) 60.35 #24 of 50 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet SL (B0) Accuracy (8 emotion) 60.34 #25 of 50 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet SL+ SSL in-painting-pl + 20% train (B0) Accuracy (8 emotion) 55.36 #34 of 50 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet SL+ SSL puzzling + 20% train (B0) Accuracy (8 emotion) 54.98 #35 of 50 Archive leaderboard report
Facial Expression Recognition (FER) AffectNet SL + 20% train (B0) Accuracy (8 emotion) 52.46 #37 of 50 Archive leaderboard report
Facial Expression Recognition (FER) CK+ Nonlinear eval on SL + SSL puzzling (B0) Accuracy (7 emotion) 98.23 #6 of 7 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAdabeliefAverage PoolingBatch NormalizationConvolutionDense ConnectionsDepthwise ConvolutionDepthwise Separable ConvolutionDropoutEfficientNetInverted Residual BlockJigsawLabel SmoothingPointwise ConvolutionReLUSigmoid ActivationSqueeze-and-Excitation Block

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections