TripletGAN: Training Generative Model with Triplet Loss
arXiv:1711.05084
Abstract
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.
References in corpus (10)
- Adam: A Method for Stochastic Optimization
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
- Improved Techniques for Training GANs
- Energy-based Generative Adversarial Network
- BEGAN: Boundary Equilibrium Generative Adversarial Networks
- Unrolled Generative Adversarial Networks
- Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
- On integral probability metrics, ϕ-divergences and binary classification
- Distributional Adversarial Networks
- Training Triplet Networks with GAN