Sample4Geo: Hard Negative Sampling For Cross-View Geo-Localisation

by   Fabian Deuser, et al.

Cross-View Geo-Localisation is still a challenging task where additional modules, specific pre-processing or zooming strategies are necessary to determine accurate positions of images. Since different views have different geometries, pre-processing like polar transformation helps to merge them. However, this results in distorted images which then have to be rectified. Adding hard negatives to the training batch could improve the overall performance but with the default loss functions in geo-localisation it is difficult to include them. In this article, we present a simplified but effective architecture based on contrastive learning with symmetric InfoNCE loss that outperforms current state-of-the-art results. Our framework consists of a narrow training pipeline that eliminates the need of using aggregation modules, avoids further pre-processing steps and even increases the generalisation capability of the model to unknown regions. We introduce two types of sampling strategies for hard negatives. The first explicitly exploits geographically neighboring locations to provide a good starting point. The second leverages the visual similarity between the image embeddings in order to mine hard negative samples. Our work shows excellent performance on common cross-view datasets like CVUSA, CVACT, University-1652 and VIGOR. A comparison between cross-area and same-area settings demonstrate the good generalisation capability of our model.


page 4

page 8

page 12

page 13


Human eye inspired log-polar pre-processing for neural networks

In this paper we draw inspiration from the human visual system, and pres...

Hard Negative Sampling Strategies for Contrastive Representation Learning

One of the challenges in contrastive learning is the selection of approp...

Pre-processing Image using Brightening, CLAHE and RETINEX

This paper focuses on finding the most optimal pre-processing methods co...

Contrastive Learning with Hard Negative Samples

We consider the question: how can you sample good negative examples for ...

On Negative Sampling for Contrastive Audio-Text Retrieval

This paper investigates negative sampling for contrastive learning in th...

Understanding Hard Negatives in Noise Contrastive Estimation

The choice of negative examples is important in noise contrastive estima...

CrOC: Cross-View Online Clustering for Dense Visual Representation Learning

Learning dense visual representations without labels is an arduous task ...

Please sign up or login with your details

Forgot password? Click here to reset