Dynamic Adaptive Threshold based Learning for Noisy Annotations Robust Facial Expression Recognition

by   Darshan Gera, et al.

The real-world facial expression recognition (FER) datasets suffer from noisy annotations due to crowd-sourcing, ambiguity in expressions, the subjectivity of annotators and inter-class similarity. However, the recent deep networks have strong capacity to memorize the noisy annotations leading to corrupted feature embedding and poor generalization. To handle noisy annotations, we propose a dynamic FER learning framework (DNFER) in which clean samples are selected based on dynamic class specific threshold during training. Specifically, DNFER is based on supervised training using selected clean samples and unsupervised consistent training using all the samples. During training, the mean posterior class probabilities of each mini-batch is used as dynamic class-specific threshold to select the clean samples for supervised training. This threshold is independent of noise rate and does not need any clean data unlike other methods. In addition, to learn from all samples, the posterior distributions between weakly-augmented image and strongly-augmented image are aligned using an unsupervised consistency loss. We demonstrate the robustness of DNFER on both synthetic as well as on real noisy annotated FER datasets like RAFDB, FERPlus, SFEW and AffectNet.


page 1

page 2

page 3

page 4


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

The hindering problem in facial expression recognition (FER) is the pres...

Consensual Collaborative Training And Knowledge Distillation Based Facial Expression Recognition Under Noisy Annotations

Presence of noise in the labels of large scale facial expression dataset...

Identifying Mislabeled Data using the Area Under the Margin Ranking

Not all data in a typical training set help with generalization; some sa...

Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training

Facial expression recognition (FER) in the wild is crucial for building ...

A Robust Optimization Method for Label Noisy Datasets Based on Adaptive Threshold: Adaptive-k

SGD does not produce robust results on datasets with label noise. Becaus...

Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition

Due to the subjective annotation and the inherent interclass similarity ...

Disjoint Contrastive Regression Learning for Multi-Sourced Annotations

Large-scale datasets are important for the development of deep learning ...

Please sign up or login with your details

Forgot password? Click here to reset