Improved Embeddings With Easy Positive Triplet Mining

Abstract

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. In this paper, we propose 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 we call "Easy Positive" mining. We provide a collection of experiments and visualizations that highlight that 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, Stan

Stats

• citations101
• S2 citations—
• github stars0
• HF likes0
• heat score15.06
• arxiv keyxuan2019improved

Related papers

• Loop: Looking For Optimal Hard Negative Embeddings For Deep Metric Learning (2021)8.82
• Visualizing How Embeddings Generalize (2019)0.00
• Learning Embeddings For Product Visual Search With Triplet Loss And Online Sampling (2018)0.00
• Fast Training Of Triplet-based Deep Binary Embedding Networks (2016)14.62
• Enhancing Remote Sensing Image Retrieval With Triplet Deep Metric Learning Network (2019)14.58
• Hard Negative Examples Are Hard, But Useful (2020)14.76
• Dynamic Sampling For Deep Metric Learning (2020)5.84
• Deep Metric Learning Beyond Binary Supervision (2019)14.39