# Adaptive Global-Local Representation Learning and Selection for Cross-Domain Facial Expression Recognition

arXiv: https://arxiv.org/abs/2401.11085 · HTML: https://mlsanity.com/paper/2401.11085/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 66 references that are in the map.
- First posted on arXiv 20 Jan 2024.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Challenges in Representation Learning: A report on three machine learning contests](https://mlsanity.com/paper/1307.0414/) (2013)
- [Deep Facial Expression Recognition: A Survey](https://mlsanity.com/paper/1804.08348/) (2018)
- [Sliced Wasserstein Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1903.04064/) (2019)
- [Unbalanced minibatch Optimal Transport; applications to Domain Adaptation](https://mlsanity.com/paper/2103.03606/) (2021)
- [Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition](https://mlsanity.com/paper/2009.09450/) (2020)
- [From Facial Expression Recognition to Interpersonal Relation Prediction](https://mlsanity.com/paper/1609.06426/) (2016)
- [Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning](https://mlsanity.com/paper/2008.00923/) (2020)
- [RestoreFormer++: Towards Real-World Blind Face Restoration from Undegraded Key-Value Pairs](https://mlsanity.com/paper/2308.07228/) (2023)
- [A Deeper Look at Facial Expression Dataset Bias](https://mlsanity.com/paper/1904.11150/) (2019)
- [Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition](https://mlsanity.com/paper/2008.00859/) (2020)
- [Spatial-Temporal Knowledge-Embedded Transformer for Video Scene Graph Generation](https://mlsanity.com/paper/2309.13237/) (2023)
- [Cross-Database Micro-Expression Recognition: A Benchmark](https://mlsanity.com/paper/1812.07742/) (2018)
- [Exploiting Local Feature Patterns for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1811.05042/) (2018)
- [Deep Multi-task Learning for Facial Expression Recognition and Synthesis Based on Selective Feature Sharing](https://mlsanity.com/paper/2007.04514/) (2020)
- [When Facial Expression Recognition Meets Few-Shot Learning: A Joint and Alternate Learning Framework](https://mlsanity.com/paper/2201.06781/) (2022)
- [Learn-to-Decompose: Cascaded Decomposition Network for Cross-Domain Few-Shot Facial Expression Recognition](https://mlsanity.com/paper/2207.07973/) (2022)
- [Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition](https://mlsanity.com/paper/2210.05246/) (2022)
- [ACDC: Online Unsupervised Cross-Domain Adaptation](https://mlsanity.com/paper/2110.01326/) (2021)
- [Pose-aware Adversarial Domain Adaptation for Personalized Facial Expression Recognition](https://mlsanity.com/paper/2007.05932/) (2020)

## Built on by (most cited first, 4 of 4)

- [ResEmoteNet: Bridging Accuracy and Loss Reduction in Facial Emotion Recognition](https://mlsanity.com/paper/2409.10545/) (2024)
- [Knowledge-Enhanced Facial Expression Recognition with Emotional-to-Neutral Transformation](https://mlsanity.com/paper/2409.08598/) (2024)
- [Graph-Attention Network with Adversarial Domain Alignment for Robust Cross-Domain Facial Expression Recognition](https://mlsanity.com/paper/2512.00641/) (2025)
- [Smile on the Face, Sadness in the Eyes: Bridging the Emotion Gap with a Multimodal Dataset of Eye and Facial Behaviors](https://mlsanity.com/paper/2512.16485/) (2025)

## Abstract (arXiv)

Domain shift poses a significant challenge in Cross-Domain Facial Expression Recognition (CD-FER) due to the distribution variation across different domains. Current works mainly focus on learning domain-invariant features through global feature adaptation, while neglecting the transferability of local features. Additionally, these methods lack discriminative supervision during training on target datasets, resulting in deteriorated feature representation in target domain. To address these limitations, we propose an Adaptive Global-Local Representation Learning and Selection (AGLRLS) framework. The framework incorporates global-local adversarial adaptation and semantic-aware pseudo label generation to enhance the learning of domain-invariant and discriminative feature during training. Meanwhile, a global-local prediction consistency learning is introduced to improve classification results during inference. Specifically, the framework consists of separate global-local adversarial learning modules that learn domain-invariant global and local features independently. We also design a semantic-aware pseudo label generation module, which computes semantic labels based on global and local features. Moreover, a novel dynamic threshold strategy is employed to learn the optimal thresholds by leveraging independent prediction of global and local features, ensuring filtering out the unreliable pseudo labels while retaining reliable ones. These labels are utilized for model optimization through the adversarial learning process in an end-to-end manner. During inference, a global-local prediction consistency module is developed to automatically learn an optimal result from multiple predictions. We conduct comprehensive experiments and analysis based on a fair evaluation benchmark. The results demonstrate that the proposed framework outperforms the current competing methods by a substantial margin.