Softmax Dissection: Towards Understanding Intra- and Inter-Class Objective for Embedding Learning
Softmax Dissection: Towards Understanding Intra- and Inter-Class Objective for Embedding Learning
The softmax loss and its variants are widely used as objectives for embedding learning applications like face recognition. However, the intra- and inter-class objectives in Softmax 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 …