# High Semantic Features for the Continual Learning of Complex Emotions: a Lightweight Solution

arXiv: https://arxiv.org/abs/2510.13534 · HTML: https://mlsanity.com/paper/2510.13534/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 32 references that are in the map.
- First posted on arXiv 15 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [Continual Learning with Deep Generative Replay](https://mlsanity.com/paper/1705.08690/) (2017)
- [FOSTER: Feature Boosting and Compression for Class-Incremental Learning](https://mlsanity.com/paper/2204.04662/) (2022)
- [Class-Incremental Learning: A Survey](https://mlsanity.com/paper/2302.03648/) (2023)
- [Always Be Dreaming: A New Approach for Data-Free Class-Incremental Learning](https://mlsanity.com/paper/2106.09701/) (2021)
- [Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2203.06359/) (2022)
- [Divide and not forget: Ensemble of selectively trained experts in Continual Learning](https://mlsanity.com/paper/2401.10191/) (2024)
- [AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors](https://mlsanity.com/paper/2403.04697/) (2024)
- [Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor](https://mlsanity.com/paper/2204.13349/) (2022)
- [Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic Features](https://mlsanity.com/paper/2308.06197/) (2023)

## Abstract (arXiv)

Incremental learning is a complex process due to potential catastrophic forgetting of old tasks when learning new ones. This is mainly due to transient features that do not fit from task to task. In this paper, we focus on complex emotion recognition. First, we learn basic emotions and then, incrementally, like humans, complex emotions. We show that Action Units, describing facial muscle movements, are non-transient, highly semantical features that outperform those extracted by both shallow and deep convolutional neural networks. Thanks to this ability, our approach achieves interesting results when learning incrementally complex, compound emotions with an accuracy of 0.75 on the CFEE dataset and can be favorably compared to state-of-the-art results. Moreover, it results in a lightweight model with a small memory footprint.