A ConvNeXt-Based Network for Aerial-view Geo-localization in Multiple Environment

In this technical report, we represent our solution for the ACMMM24 Multimedia Drone Satellite Matching Challenge in Multiple Environment. Our solution targets at learning discriminative descriptors to cope with the environmental changes when aerial-view geo-localization in open scenarios. Specifically, our network is based on the square-ring partition and employs ConvNeXt with the stride of the last down-sample layer set to 1 as the backbone to extract richer fine-grained information. In addition, since drone-view images contain environmental distraction, we adopt two loss functions to strengthen the optimization constraints on the designed network. Experiments show that our method can effectively match multi-environment drone-view images with satellite images and achieve competitive accuracy on University160k-WX.