# Efficient Facial Feature Learning with Wide Ensemble-based Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2001.06338 · HTML: https://mlsanity.com/paper/2001.06338/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jan 2020.

## Built on by (most cited first, 24 of 24)

- [GAN-Control: Explicitly Controllable GANs](https://mlsanity.com/paper/2101.02477/) (2021)
- [Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition](https://mlsanity.com/paper/2109.07270/) (2021)
- [SPACE: Speech-driven Portrait Animation with Controllable Expression](https://mlsanity.com/paper/2211.09809/) (2022)
- [Facial expression and attributes recognition based on multi-task learning of lightweight neural networks](https://mlsanity.com/paper/2103.17107/) (2021)
- [Leveraging Recent Advances in Deep Learning for Audio-Visual Emotion Recognition](https://mlsanity.com/paper/2103.09154/) (2021)
- [One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations](https://mlsanity.com/paper/2210.07883/) (2022)
- [Detection and Localization of Facial Expression Manipulations](https://mlsanity.com/paper/2103.08134/) (2021)
- [Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognition](https://mlsanity.com/paper/2307.11404/) (2023)
- [Teacher-Student Training and Triplet Loss to Reduce the Effect of Drastic Face Occlusion](https://mlsanity.com/paper/2111.10561/) (2021)
- [Using Self-Supervised Auxiliary Tasks to Improve Fine-Grained Facial Representation](https://mlsanity.com/paper/2105.06421/) (2021)
- [CIAO! A Contrastive Adaptation Mechanism for Non-Universal Facial Expression Recognition](https://mlsanity.com/paper/2208.07221/) (2022)
- [Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training](https://mlsanity.com/paper/2107.05736/) (2021)
- [GASP: Gated Attention For Saliency Prediction](https://mlsanity.com/paper/2206.04590/) (2022)
- [Dynamic Adaptive Threshold based Learning for Noisy Annotations Robust Facial Expression Recognition](https://mlsanity.com/paper/2208.10221/) (2022)
- [Learning Diversified Feature Representations for Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2210.09381/) (2022)
- [Complex Facial Expression Recognition Using Deep Knowledge Distillation of Basic Features](https://mlsanity.com/paper/2308.06197/) (2023)
- [Contrastive Learning of View-Invariant Representations for Facial Expressions Recognition](https://mlsanity.com/paper/2311.06852/) (2023)
- [IDperturb: Enhancing Variation in Synthetic Face Generation via Angular Perturbation](https://mlsanity.com/paper/2602.18831/) (2026)
- [Domain Adaptation for Facial Expression Classifier via Domain Discrimination and Gradient Reversal](https://mlsanity.com/paper/2106.01467/) (2021)
- [Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations](https://mlsanity.com/paper/2107.04746/) (2021)
- [Auxiliary Class Based Multiple Choice Learning](https://mlsanity.com/paper/2108.02949/) (2021)
- [The Many Faces of Anger: A Multicultural Video Dataset of Negative Emotions in the Wild (MFA-Wild)](https://mlsanity.com/paper/2112.05267/) (2021)
- [A comparative study of emotion recognition methods using facial expressions](https://mlsanity.com/paper/2212.03102/) (2022)
- [VerA: Versatile Anonymization Applicable to Clinical Facial Photographs](https://mlsanity.com/paper/2312.02124/) (2023)

## Abstract (arXiv)

Ensemble methods, traditionally built with independently trained de-correlated models, have proven to be efficient methods for reducing the remaining residual generalization error, which results in robust and accurate methods for real-world applications. In the context of deep learning, however, training an ensemble of deep networks is costly and generates high redundancy which is inefficient. In this paper, we present experiments on Ensembles with Shared Representations (ESRs) based on convolutional networks to demonstrate, quantitatively and qualitatively, their data processing efficiency and scalability to large-scale datasets of facial expressions. We show that redundancy and computational load can be dramatically reduced by varying the branching level of the ESR without loss of diversity and generalization power, which are both important for ensemble performance. Experiments on large-scale datasets suggest that ESRs reduce the remaining residual generalization error on the AffectNet and FER+ datasets, reach human-level performance, and outperform state-of-the-art methods on facial expression recognition in the wild using emotion and affect concepts.