# BReG-NeXt: Facial Affect Computing Using Adaptive Residual Networks With Bounded Gradient

arXiv: https://arxiv.org/abs/2004.08495 · HTML: https://mlsanity.com/paper/2004.08495/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Apr 2020.

## Built on by (most cited first, 13 of 13)

- [Self-supervised Contrastive Learning of Multi-view Facial Expressions](https://mlsanity.com/paper/2108.06723/) (2021)
- [Exploiting Emotional Dependencies with Graph Convolutional Networks for Facial Expression Recognition](https://mlsanity.com/paper/2106.03487/) (2021)
- [GRATIS: Deep Learning Graph Representation with Task-specific Topology and Multi-dimensional Edge Features](https://mlsanity.com/paper/2211.12482/) (2022)
- [AffectNet+: A Database for Enhancing Facial Expression Recognition with Soft-Labels](https://mlsanity.com/paper/2410.22506/) (2024)
- [Optimal Transport-based Identity Matching for Identity-invariant Facial Expression Recognition](https://mlsanity.com/paper/2209.12172/) (2022)
- [Face Trees for Expression Recognition](https://mlsanity.com/paper/2112.02487/) (2021)
- [Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition](https://mlsanity.com/paper/2210.05246/) (2022)
- [FaceTopoNet: Facial Expression Recognition using Face Topology Learning](https://mlsanity.com/paper/2209.06322/) (2022)
- [Mutilmodal Feature Extraction and Attention-based Fusion for Emotion Estimation in Videos](https://mlsanity.com/paper/2303.10421/) (2023)
- [Contrastive Learning of View-Invariant Representations for Facial Expressions Recognition](https://mlsanity.com/paper/2311.06852/) (2023)
- [A Lightweight Attention-based Deep Network via Multi-Scale Feature Fusion for Multi-View Facial Expression Recognition](https://mlsanity.com/paper/2403.14318/) (2024)
- [A Perception CNN for Facial Expression Recognition](https://mlsanity.com/paper/2512.06422/) (2025)
- [Finding Emotions in Faces: A Meta-Classifier](https://mlsanity.com/paper/2208.09678/) (2022)

## Abstract (arXiv)

This paper introduces BReG-NeXt, a residual-based network architecture using a function wtih bounded derivative instead of a simple shortcut path (a.k.a. identity mapping) in the residual units for automatic recognition of facial expressions based on the categorical and dimensional models of affect. Compared to ResNet, our proposed adaptive complex mapping results in a shallower network with less numbers of training parameters and floating point operations per second (FLOPs). Adding trainable parameters to the bypass function further improves fitting and training the network and hence recognizing subtle facial expressions such as contempt with a higher accuracy. We conducted comprehensive experiments on the categorical and dimensional models of affect on the challenging in-the-wild databases of AffectNet, FER2013, and Affect-in-Wild. Our experimental results show that our adaptive complex mapping approach outperforms the original ResNet consisting of a simple identity mapping as well as other state-of-the-art methods for Facial Expression Recognition (FER). Various metrics are reported in both affect models to provide a comprehensive evaluation of our method. In the categorical model, BReG-NeXt-50 with only 3.1M training parameters and 15 MFLOPs, achieves 68.50% and 71.53% accuracy on AffectNet and FER2013 databases, respectively. In the dimensional model, BReG-NeXt achieves 0.2577 and 0.2882 RMSE value on AffectNet and Affect-in-Wild databases, respectively.