TripletGAN: Training Generative Model with Triplet Loss
This is an incremental improvement for GAN training, addressing mode collapse and convergence issues in generative modeling.
The paper tackles the problem of training generative adversarial networks (GANs) by proposing TripletGAN, which replaces the discriminator's classification loss with triplet loss, resulting in theoretical convergence to the target distribution and prevention of mode collapse, as demonstrated experimentally.
As an effective way of metric learning, triplet loss has been widely used in many deep learning tasks, including face recognition and person-ReID, leading to many states of the arts. The main innovation of triplet loss is using feature map to replace softmax in the classification task. Inspired by this concept, we propose here a new adversarial modeling method by substituting the classification loss of discriminator with triplet loss. Theoretical proof based on IPM (Integral probability metric) demonstrates that such setting will help the generator converge to the given distribution theoretically under some conditions. Moreover, since triplet loss requires the generator to maximize distance within a class, we justify tripletGAN is also helpful to prevent mode collapse through both theory and experiment.