Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learning

Understand

The softmax loss and its variants are widely used as objectives for embedding learning, especially in applications like face recognition.

• However, the intra- and inter-class objectives in the softmax loss are entangled, therefore a well-optimized inter-class objective leads to relaxation on the intra-class objective, and vice versa.
• In this paper, we propose to dissect the softmax loss into independent intra- and inter-class objective (D-Softmax).
• With D-Softmax as objective, we can have a clear understanding of both the intra- and inter-class objective, therefore it is straightforward to tune each part to the best state.