Hyperparameter Optimization and Boosting for Classifying Facial Expressions: How good can a "Null" Model be?

by   James Bergstra, et al.

One of the goals of the ICML workshop on representation and learning is to establish benchmark scores for a new data set of labeled facial expressions. This paper presents the performance of a "Null" model consisting of convolutions with random weights, PCA, pooling, normalization, and a linear readout. Our approach focused on hyperparameter optimization rather than novel model components. On the Facial Expression Recognition Challenge held by the Kaggle website, our hyperparameter optimization approach achieved a score of 60 construction variant that combines hyperparameter optimization with the construction of ensembles. This algorithm constructed an ensemble of four models that scored 65.5 among the 56 challenge participants. It is worth noting that our approach was developed prior to the release of the data set, and applied without modification; our strong competition performance suggests that the TPE hyperparameter optimization algorithm and domain expertise encoded in our Null model can generalize to new image classification data sets.


page 1

page 2

page 3

page 4


Learning Stylized Character Expressions from Humans

We present DeepExpr, a novel expression transfer system from humans to m...

Learning from Synthetic Data: Facial Expression Classification based on Ensemble of Multi-task Networks

Facial expression in-the-wild is essential for various interactive compu...

Recognizing Facial Expressions in the Wild using Multi-Architectural Representations based Ensemble Learning with Distillation

Facial expressions are the most common universal forms of body language....

Challenges in Representation Learning: A report on three machine learning contests

The ICML 2013 Workshop on Challenges in Representation Learning focused ...

Facial Expression Representation and Recognition Using 2DHLDA, Gabor Wavelets, and Ensemble Learning

In this paper, a novel method for representation and recognition of the ...

Learning to Amend Facial Expression Representation via De-albino and Affinity

Facial Expression Recognition (FER) is a classification task that points...

Please sign up or login with your details

Forgot password? Click here to reset