In order to have improved embeddings with easy positive triplet mining, this paper proposes an alternative, loosened embedding strategy that requires the embedding function only map each training image to the most similar examples from the same class, an approach the authors call "Easy Positive" mining.
Deep metric learning seeks to define an embedding where semantically similar images are embedded to nearby locations, and semantically dissimilar images are embedded to distant locations. Substantial work has focused on loss functions and strategies to learn these embeddings by pushing images from the same class as close together in the embedding space as possible. The current project provides a collection of experiments and visualizations that show this Easy Positive mining leads to embeddings that are more flexible and generalize better to new unseen data. This simple mining strategy yields recall performance that exceeds state of the art approaches (including those with complicated loss functions and ensemble methods) on image retrieval datasets, including CUB, Stanford Online Products, In-Shop Clothes and Hotels-50K. The code is available at: https://github.com/littleredxh/EasyPositiveHardNegative (publisher abstract modified)