Stochastic Attraction-repulsion Embedding For Large Scale Image Localization

Abstract

This paper tackles the problem of large-scale image-based localization (IBL) where the spatial location of a query image is determined by finding out the most similar reference images in a large database. For solving this problem, a critical task is to learn discriminative image representation that captures informative information relevant for localization. We propose a novel representation learning method having higher location-discriminating power. It provides the following contributions: 1) we represent a place (location) as a set of exemplar images depicting the same landmarks and aim to maximize similarities among intra-place images while minimizing similarities among inter-place images; 2) we model a similarity measure as a probability distribution on L_2-metric distances between intra-place and inter-place image representations; 3) we propose a new Stochastic Attraction and Repulsion Embedding (SARE) loss function minimizing the KL divergence between the learned and the actual p

Stats

• citations87
• S2 citations—
• github stars30
• HF likes0
• heat score17.57
• arxiv keyliu2018stochastic

Related papers

• Leveraging Efficientnet And Contrastive Learning For Accurate Global-scale Location Estimation (2021)9.03
• Self-supervising Fine-grained Region Similarities For Large-scale Image Localization (2020)15.85
• Benchmarking Image Retrieval For Visual Localization (2020)17.78
• Multiview Image-based Localization (2025)0.00
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Investigating The Role Of Image Retrieval For Visual Localization -- An Exhaustive Benchmark (2022)16.58
• Domain-invariant Similarity Activation Map Contrastive Learning For Retrieval-based Long-term Visual Localization (2020)13.72
• Learning Condition Invariant Features For Retrieval-based Localization From 1M Images (2020)0.00