Label Embedding Network: Learning Label Representation for Soft Training of Deep Networks

Understand

We propose a method, called Label Embedding Network, which can learn label representation (label embedding) during the training process of deep networks.

• With the proposed method, the label embedding is adaptively and automatically learned through back propagation.
• The original one-hot represented loss function is converted into a new loss function with soft distributions, such that the originally unrelated labels have continuous interactions with each other during the training process.
• As a result, the trained model can achieve substantially higher accuracy and with faster convergence speed.