# Class adaptive threshold and negative class guided noisy annotation robust Facial Expression Recognition

arXiv: https://arxiv.org/abs/2305.01884 · HTML: https://mlsanity.com/paper/2305.01884/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 3 May 2023.

## Builds on (most cited first, 21 of 21)

- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks](https://mlsanity.com/paper/1604.02878/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognition](https://mlsanity.com/paper/1607.08221/) (2016)
- [AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild](https://mlsanity.com/paper/1708.03985/) (2017)
- [How does Disagreement Help Generalization against Label Corruption?](https://mlsanity.com/paper/1901.04215/) (2019)
- [Challenges in Representation Learning: A report on three machine learning contests](https://mlsanity.com/paper/1307.0414/) (2013)
- [Combating noisy labels by agreement: A joint training method with co-regularization](https://mlsanity.com/paper/2003.02752/) (2020)
- [Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution](https://mlsanity.com/paper/1608.01041/) (2016)
- [Suppressing Uncertainties for Large-Scale Facial Expression Recognition](https://mlsanity.com/paper/2002.10392/) (2020)
- [NLNL: Negative Learning for Noisy Labels](https://mlsanity.com/paper/1908.07387/) (2019)
- [Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition](https://mlsanity.com/paper/1905.04075/) (2019)
- [Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition](https://mlsanity.com/paper/2104.00232/) (2021)
- [Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition](https://mlsanity.com/paper/2207.10299/) (2022)
- [Feature Decomposition and Reconstruction Learning for Effective Facial Expression Recognition](https://mlsanity.com/paper/2104.05160/) (2021)
- [Occlusion-Adaptive Deep Network for Robust Facial Expression Recognition](https://mlsanity.com/paper/2005.06040/) (2020)
- [Noisy Concurrent Training for Efficient Learning under Label Noise](https://mlsanity.com/paper/2009.08325/) (2020)
- [Landmark Guidance Independent Spatio-channel Attention and Complementary Context Information based Facial Expression Recognition](https://mlsanity.com/paper/2007.10298/) (2020)
- [Dynamic Adaptive Threshold based Learning for Noisy Annotations Robust Facial Expression Recognition](https://mlsanity.com/paper/2208.10221/) (2022)

## Abstract (arXiv)

The hindering problem in facial expression recognition (FER) is the presence of inaccurate annotations referred to as noisy annotations in the datasets. These noisy annotations are present in the datasets inherently because the labeling is subjective to the annotator, clarity of the image, etc. Recent works use sample selection methods to solve this noisy annotation problem in FER. In our work, we use a dynamic adaptive threshold to separate confident samples from non-confident ones so that our learning won't be hampered due to non-confident samples. Instead of discarding the non-confident samples, we impose consistency in the negative classes of those non-confident samples to guide the model to learn better in the positive class. Since FER datasets usually come with 7 or 8 classes, we can correctly guess a negative class by 85% probability even by choosing randomly. By learning "which class a sample doesn't belong to", the model can learn "which class it belongs to" in a better manner. We demonstrate proposed framework's effectiveness using quantitative as well as qualitative results. Our method performs better than the baseline by a margin of 4% to 28% on RAFDB and 3.3% to 31.4% on FERPlus for various levels of synthetic noisy labels in the aforementioned datasets.