Each Part Matters: Local Patterns Facilitate Cross-view Geo-localization

Abstract

Cross-view geo-localization is to spot images of the same geographic target from different platforms, e.g., drone-view cameras and satellites. It is challenging in the large visual appearance changes caused by extreme viewpoint variations. Existing methods usually concentrate on mining the fine-grained feature of the geographic target in the image center, but underestimate the contextual information in neighbor areas. In this work, we argue that neighbor areas can be leveraged as auxiliary information, enriching discriminative clues for geolocalization. Specifically, we introduce a simple and effective deep neural network, called Local Pattern Network (LPN), to take advantage of contextual information in an end-to-end manner. Without using extra part estimators, LPN adopts a square-ring feature partition strategy, which provides the attention according to the distance to the image center. It eases the part matching and enables the part-wise representation learning. Owing to the square-ring partition design, the proposed LPN has good scalability to rotation variations and achieves competitive results on three prevailing benchmarks, i.e., University-1652, CVUSA and CVACT. Besides, we also show the proposed LPN can be easily embedded into other frameworks to further boost performance.

arXiv commentaccepted by TCSVT

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• FaceNet: A Unified Embedding for Face Recognition and Clustering
• Pedestrian Alignment Network for Large-scale Person Re-identification
• Dual-Path Convolutional Image-Text Embeddings with Instance Loss
• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification
• STA: Spatial-Temporal Attention for Large-Scale Video-based Person Re-Identification

Cited by in corpus (10)

• A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization
• SDPL: Shifting-Dense Partition Learning for UAV-View Geo-Localization
• Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval
• Cross-view geo-localization: a survey
• Beyond Geo-localization: Fine-grained Orientation of Street-view Images by Cross-view Matching with Satellite Imagery with Supplementary Materials
• StepNet: Spatial-temporal Part-aware Network for Isolated Sign Language Recognition
• Style Alignment based Dynamic Observation Method for UAV-View Geo-localization
• Multi-weather Cross-view Geo-localization Using Denoising Diffusion Models
• UPANets: Learning from the Universal Pixel Attention Networks
• PetalView: Fine-grained Location and Orientation Extraction of Street-view Images via Cross-view Local Search with Supplementary Materials