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

by   Darshan Gera, et al.

Presence of noise in the labels of large scale facial expression datasets has been a key challenge towards Facial Expression Recognition (FER) in the wild. During early learning stage, deep networks fit on clean data. Then, eventually, they start overfitting on noisy labels due to their memorization ability, which limits FER performance. This work proposes an effective training strategy in the presence of noisy labels, called as Consensual Collaborative Training (CCT) framework. CCT co-trains three networks jointly using a convex combination of supervision loss and consistency loss, without making any assumption about the noise distribution. A dynamic transition mechanism is used to move from supervision loss in early learning to consistency loss for consensus of predictions among networks in the later stage. Inference is done using a single network based on a simple knowledge distillation scheme. Effectiveness of the proposed framework is demonstrated on synthetic as well as real noisy FER datasets. In addition, a large test subset of around 5K images is annotated from the FEC dataset using crowd wisdom of 16 different annotators and reliable labels are inferred. CCT is also validated on it. State-of-the-art performance is reported on the benchmark FER datasets RAFDB (90.84 AffectNet (66


page 3

page 7

page 9


Affect Expression Behaviour Analysis in the Wild using Consensual Collaborative Training

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

Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution

Crowd sourcing has become a widely adopted scheme to collect ground trut...

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

The real-world facial expression recognition (FER) datasets suffer from ...

Label quality in AffectNet: results of crowd-based re-annotation

AffectNet is one of the most popular resources for facial expression rec...

LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise

Facial expression recognition (FER) remains a challenging task due to th...

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

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

Noisy Student Training using Body Language Dataset Improves Facial Expression Recognition

Facial expression recognition from videos in the wild is a challenging t...

Please sign up or login with your details

Forgot password? Click here to reset