Deep Metric Learning Beyond Binary Supervision

Abstract

Metric Learning for visual similarity has mostly adopted binary supervision indicating whether a pair of images are of the same class or not. Such a binary indicator covers only a limited subset of image relations, and is not sufficient to represent semantic similarity between images described by continuous and/or structured labels such as object poses, image captions, and scene graphs. Motivated by this, we present a novel method for deep metric learning using continuous labels. First, we propose a new triplet loss that allows distance ratios in the label space to be preserved in the learned metric space. The proposed loss thus enables our model to learn the degree of similarity rather than just the order. Furthermore, we design a triplet mining strategy adapted to metric learning with continuous labels. We address three different image retrieval tasks with continuous labels in terms of human poses, room layouts and image captions, and demonstrate the superior performance of our appro

Stats

• citations82
• S2 citations—
• github stars0
• HF likes0
• heat score14.39
• arxiv keykim2019deep

Related papers

• Sharing Matters For Generalization In Deep Metric Learning (2020)8.35
• Three Things To Know About Deep Metric Learning (2024)0.00
• Human Motion Analysis With Deep Metric Learning (2018)11.58
• Deep Metric Learning For Computer Vision: A Brief Overview (2023)6.77
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24
• Enhancing Remote Sensing Image Retrieval With Triplet Deep Metric Learning Network (2019)14.58
• Dynamic Sampling For Deep Metric Learning (2020)5.84
• Integrating Language Guidance Into Vision-based Deep Metric Learning (2022)14.04