Training Triplet Networks With GAN

Abstract

Triplet networks are widely used models that are characterized by good performance in classification and retrieval tasks. In this work we propose to train a triplet network by putting it as the discriminator in Generative Adversarial Nets (GANs). We make use of the good capability of representation learning of the discriminator to increase the predictive quality of the model. We evaluated our approach on Cifar10 and MNIST datasets and observed significant improvement on the classification performance using the simple k-nn method.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzieba2017training

Related papers

• Semi-supervised Learning With Bidirectional Gans (2018)4.52
• Neighborhood Watch: Representation Learning With Local-margin Triplet Loss And Sampling Strategy For K-nearest-neighbor Image Classification (2019)0.00
• Inverting The Generator Of A Generative Adversarial Network (2016)17.61
• Deep Triplet Ranking Networks For One-shot Recognition (2018)0.00
• Enhancing Remote Sensing Image Retrieval With Triplet Deep Metric Learning Network (2019)14.58
• Fast Training Of Triplet-based Deep Binary Embedding Networks (2016)14.62
• Triplet-based Deep Similarity Learning For Person Re-identification (2018)10.61
• Incorporating Intra-class Variance To Fine-grained Visual Recognition (2017)11.67