Search Results for author:
Found 2 papers, 1 papers with code
Contrastive Bayesian Analysis for Deep Metric Learning
Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same class closer and push negative samples from different classes away from each other.
Relative Order Analysis and Optimization for Unsupervised Deep Metric Learning
During training, this relative order prediction network and the feature embedding network are tightly coupled, providing mutual constraints to each other to improve overall metric learning performance in a cooperative manner.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
