# Peak-Piloted Deep Network for Facial Expression Recognition

arXiv: https://arxiv.org/abs/1607.06997 · HTML: https://mlsanity.com/paper/1607.06997/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jul 2016.

## Built on by (most cited first, 22 of 22)

- [Analysing Affective Behavior in the second ABAW2 Competition](https://mlsanity.com/paper/2106.15318/) (2021)
- [FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos](https://mlsanity.com/paper/2203.09463/) (2022)
- [Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition](https://mlsanity.com/paper/2104.05160/) (2021)
- [Expression Snippet Transformer for Robust Video-based Facial Expression Recognition](https://mlsanity.com/paper/2109.08409/) (2021)
- [Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild](https://mlsanity.com/paper/2205.04749/) (2022)
- [Responsible AI: Gender bias assessment in emotion recognition](https://mlsanity.com/paper/2103.11436/) (2021)
- [An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wild](https://mlsanity.com/paper/2107.03465/) (2021)
- [Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher](https://mlsanity.com/paper/2205.14361/) (2022)
- [Spatiotemporal Contrastive Learning of Facial Expressions in Videos](https://mlsanity.com/paper/2108.03064/) (2021)
- [An EEG-Based Multi-Modal Emotion Database with Both Posed and Authentic Facial Actions for Emotion Analysis](https://mlsanity.com/paper/2203.15829/) (2022)
- [Mid-level Representation Enhancement and Graph Embedded Uncertainty Suppressing for Facial Expression Recognition](https://mlsanity.com/paper/2207.13235/) (2022)
- [MIDAS: Mixing Ambiguous Data with Soft Labels for Dynamic Facial Expression Recognition](https://mlsanity.com/paper/2503.00202/) (2025)
- [Regional Attention Network (RAN) for Head Pose and Fine-grained Gesture Recognition](https://mlsanity.com/paper/2101.06634/) (2021)
- [Multi-Branch Deep Radial Basis Function Networks for Facial Emotion Recognition](https://mlsanity.com/paper/2109.03336/) (2021)
- [Progressive Spatio-Temporal Bilinear Network with Monte Carlo Dropout for Landmark-based Facial Expression Recognition with Uncertainty Estimation](https://mlsanity.com/paper/2106.04332/) (2021)
- [Exp-Graph: How Connections Learn Facial Attributes in Graph-based Expression Recognition](https://mlsanity.com/paper/2507.14608/) (2025)
- [MAFER: a Multi-resolution Approach to Facial Expression Recognition](https://mlsanity.com/paper/2105.02481/) (2021)
- [Enhancing Ambiguous Dynamic Facial Expression Recognition with Soft Label-based Data Augmentation](https://mlsanity.com/paper/2506.20867/) (2025)
- [On the Pitfalls of Learning with Limited Data: A Facial Expression Recognition Case Study](https://mlsanity.com/paper/2104.02653/) (2021)
- [Domain Adaptation for Facial Expression Classifier via Domain Discrimination and Gradient Reversal](https://mlsanity.com/paper/2106.01467/) (2021)
- [Adaptive Graph-Based Feature Normalization for Facial Expression Recognition](https://mlsanity.com/paper/2207.11123/) (2022)
- [Self-Paced Neutral Expression-Disentangled Learning for Facial Expression Recognition](https://mlsanity.com/paper/2303.11840/) (2023)

## Abstract (arXiv)

Objective functions for training of deep networks for face-related recognition tasks, such as facial expression recognition (FER), usually consider each sample independently. In this work, we present a novel peak-piloted deep network (PPDN) that uses a sample with peak expression (easy sample) to supervise the intermediate feature responses for a sample of non-peak expression (hard sample) of the same type and from the same subject. The expression evolving process from non-peak expression to peak expression can thus be implicitly embedded in the network to achieve the invariance to expression intensities. A special purpose back-propagation procedure, peak gradient suppression (PGS), is proposed for network training. It drives the intermediate-layer feature responses of non-peak expression samples towards those of the corresponding peak expression samples, while avoiding the inverse. This avoids degrading the recognition capability for samples of peak expression due to interference from their non-peak expression counterparts. Extensive comparisons on two popular FER datasets, Oulu-CASIA and CK+, demonstrate the superiority of the PPDN over state-ofthe-art FER methods, as well as the advantages of both the network structure and the optimization strategy. Moreover, it is shown that PPDN is a general architecture, extensible to other tasks by proper definition of peak and non-peak samples. This is validated by experiments that show state-of-the-art performance on pose-invariant face recognition, using the Multi-PIE dataset.