I want to use deep learning to train a face/non-face binary detection, what loss should I use, I think it is SigmoidCrossEntropyLoss or Hinge-loss.
Is that right, but I also wonder should I use softmax but with only two classes?
Solved – What loss function should I use for binary detection in face/non-face detection in CNN
computer visionconv-neural-networkdeep learningloss-functions
Related Question
- Cross-Entropy Loss – Choosing Between Categorical and Binary Cross-Entropy for Binary Predictions
- Solved – a binary loss, and should I use a binary loss or a softmax loss for classification
- Neural Networks – What Does It Mean ‘Loss Function Should Be Decoupled’ in Backprop for Deep Learning?: Detailed Insight
Best Answer
Hinge loss and cross entropy are generally found having similar results. Here's another post comparing different loss functions What are the impacts of choosing different loss functions in classification to approximate 0-1 loss.
Softmax is not a loss but a normalization function, it is often used together with the cross entropy loss, which is essentially equivalent to
SigmoidCrossEntropyLoss. See also Cross-Entropy or Log Likelihood in Output layer