# Towards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin

arXiv: https://arxiv.org/abs/2203.12341 · HTML: https://mlsanity.com/paper/2203.12341/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 23 Mar 2022.

## Builds on (most cited first, 24 of 24)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://mlsanity.com/paper/1708.03985/) (2017)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [Label Propagation for Deep Semi-supervised Learning](https://mlsanity.com/paper/1904.04717/) (2019)
- [Contrastive Clustering](https://mlsanity.com/paper/2009.09687/) (2020)
- [Semi-Supervised Learning with Ladder Networks](https://mlsanity.com/paper/1507.02672/) (2015)
- [Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution](https://mlsanity.com/paper/1608.01041/) (2016)
- [Suppressing Uncertainties for Large-Scale Facial Expression Recognition](https://mlsanity.com/paper/2002.10392/) (2020)
- [Dash: Semi-Supervised Learning with Dynamic Thresholding](https://mlsanity.com/paper/2109.00650/) (2021)
- [Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition](https://mlsanity.com/paper/1905.04075/) (2019)
- [Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition](https://mlsanity.com/paper/2104.00232/) (2021)
- [TransFER: Learning Relation-aware Facial Expression Representations with Transformers](https://mlsanity.com/paper/2108.11116/) (2021)
- [Jo-SRC: A Contrastive Approach for Combating Noisy Labels](https://mlsanity.com/paper/2103.13029/) (2021)
- [Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection](https://mlsanity.com/paper/2103.16368/) (2021)

## Built on by (most cited first, 30 of 32)

- [Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition](https://mlsanity.com/paper/2310.19636/) (2023)
- [DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection](https://mlsanity.com/paper/2304.13031/) (2023)
- [Towards Semi-supervised Universal Graph Classification](https://mlsanity.com/paper/2305.19598/) (2023)
- [ARBEx: Attentive Feature Extraction with Reliability Balancing for Robust Facial Expression Learning](https://mlsanity.com/paper/2305.01486/) (2023)
- [FER-former: Multi-modal Transformer for Facial Expression Recognition](https://mlsanity.com/paper/2303.12997/) (2023)
- [Exploring Facial Expression Recognition through Semi-Supervised Pretraining and Temporal Modeling](https://mlsanity.com/paper/2403.11942/) (2024)
- [Hiding Visual Information via Obfuscating Adversarial Perturbations](https://mlsanity.com/paper/2209.15304/) (2022)
- [SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data](https://mlsanity.com/paper/2410.09865/) (2024)
- [SS-MFAR : Semi-supervised Multi-task Facial Affect Recognition](https://mlsanity.com/paper/2207.09012/) (2022)
- [Exploring Large-scale Unlabeled Faces to Enhance Facial Expression Recognition](https://mlsanity.com/paper/2303.08617/) (2023)
- [Adaptive Margin Contrastive Learning for Ambiguity-aware 3D Semantic Segmentation](https://mlsanity.com/paper/2502.04111/) (2025)
- [Robust Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2502.16129/) (2025)
- [Towards Generalized Proactive Defense against Face Swapping with Contour-Hybrid Watermark](https://mlsanity.com/paper/2505.19081/) (2025)
- [Rethinking the Learning Paradigm for Facial Expression Recognition](https://mlsanity.com/paper/2209.15402/) (2022)
- [ABAW : Facial Expression Recognition in the wild](https://mlsanity.com/paper/2303.09785/) (2023)
- [Open-Set Facial Expression Recognition](https://mlsanity.com/paper/2401.12507/) (2024)
- [Knowledge-Enhanced Facial Expression Recognition with Emotional-to-Neutral Transformation](https://mlsanity.com/paper/2409.08598/) (2024)
- [DIG-FACE: De-biased Learning for Generalized Facial Expression Category Discovery](https://mlsanity.com/paper/2409.20098/) (2024)
- [Contrastive Learning of View-Invariant Representations for Facial Expressions Recognition](https://mlsanity.com/paper/2311.06852/) (2023)
- [A Generative Framework for Self-Supervised Facial Representation Learning](https://mlsanity.com/paper/2309.08273/) (2023)
- [Bridging the Gaps: Utilizing Unlabeled Face Recognition Datasets to Boost Semi-Supervised Facial Expression Recognition](https://mlsanity.com/paper/2410.17622/) (2024)
- [Ambiguity-aware Point Cloud Segmentation by Adaptive Margin Contrastive Learning](https://mlsanity.com/paper/2507.06592/) (2025)
- [SimFLE: Simple Facial Landmark Encoding for Self-Supervised Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2303.07648/) (2023)
- [A Unified Transformer-based Network for multimodal Emotion Recognition](https://mlsanity.com/paper/2308.14160/) (2023)
- [Ada-DF: An Adaptive Label Distribution Fusion Network For Facial Expression Recognition](https://mlsanity.com/paper/2404.15714/) (2024)
- [GReFEL: Geometry-Aware Reliable Facial Expression Learning under Bias and Imbalanced Data Distribution](https://mlsanity.com/paper/2410.15927/) (2024)
- [Rank-O-ToM: Unlocking Emotional Nuance Ranking to Enhance Affective Theory-of-Mind](https://mlsanity.com/paper/2503.16461/) (2025)
- [SIT-FER: Integration of Semantic-, Instance-, Text-level Information for Semi-supervised Facial Expression Recognition](https://mlsanity.com/paper/2503.18463/) (2025)
- [A Visual Self-attention Mechanism Facial Expression Recognition Network beyond Convnext](https://mlsanity.com/paper/2504.09077/) (2025)
- [Global Multiple Extraction Network for Low-Resolution Facial Expression Recognition](https://mlsanity.com/paper/2511.05938/) (2025)

## Abstract (arXiv)

Only parts of unlabeled data are selected to train models for most semi-supervised learning methods, whose confidence scores are usually higher than the pre-defined threshold (i.e., the confidence margin). We argue that the recognition performance should be further improved by making full use of all unlabeled data. In this paper, we learn an Adaptive Confidence Margin (Ada-CM) to fully leverage all unlabeled data for semi-supervised deep facial expression recognition. All unlabeled samples are partitioned into two subsets by comparing their confidence scores with the adaptively learned confidence margin at each training epoch: (1) subset I including samples whose confidence scores are no lower than the margin; (2) subset II including samples whose confidence scores are lower than the margin. For samples in subset I, we constrain their predictions to match pseudo labels. Meanwhile, samples in subset II participate in the feature-level contrastive objective to learn effective facial expression features. We extensively evaluate Ada-CM on four challenging datasets, showing that our method achieves state-of-the-art performance, especially surpassing fully-supervised baselines in a semi-supervised manner. Ablation study further proves the effectiveness of our method. The source code is available at https://github.com/hangyu94/Ada-CM.