# GAIR: Location-Aware Self-Supervised Contrastive Pre-Training with Geo-Aligned Implicit Representations

arXiv: https://arxiv.org/abs/2503.16683 · HTML: https://mlsanity.com/paper/2503.16683/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 97 references that are in the map.
- First posted on arXiv 20 Mar 2025.

## Builds on (most cited first, 30 of 58)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [RemoteCLIP: A Vision Language Foundation Model for Remote Sensing](https://mlsanity.com/paper/2306.11029/) (2023)
- [GeoChat: Grounded Large Vision-Language Model for Remote Sensing](https://mlsanity.com/paper/2311.15826/) (2023)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [SpectralGPT: Spectral Remote Sensing Foundation Model](https://mlsanity.com/paper/2311.07113/) (2023)
- [COIN: COmpression with Implicit Neural representations](https://mlsanity.com/paper/2103.03123/) (2021)
- [Implicit Diffusion Models for Continuous Super-Resolution](https://mlsanity.com/paper/2303.16491/) (2023)
- [SkySense: A Multi-Modal Remote Sensing Foundation Model Towards Universal Interpretation for Earth Observation Imagery](https://mlsanity.com/paper/2312.10115/) (2023)
- [Geography-Aware Self-Supervised Learning](https://mlsanity.com/paper/2011.09980/) (2020)
- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [Wide-Area Image Geolocalization with Aerial Reference Imagery](https://mlsanity.com/paper/1510.03743/) (2015)
- [EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domain](https://mlsanity.com/paper/2401.16822/) (2024)
- [CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders](https://mlsanity.com/paper/2311.00566/) (2023)
- [SatlasPretrain: A Large-Scale Dataset for Remote Sensing Image Understanding](https://mlsanity.com/paper/2211.15660/) (2022)

## Built on by (most cited first, 10 of 10)

- [Measuring the Intrinsic Dimension of Earth Representations](https://mlsanity.com/paper/2511.02101/) (2025)
- [LocDiff: Identifying Locations on Earth by Diffusing in the Hilbert Space](https://mlsanity.com/paper/2503.18142/) (2025)
- [A Genealogy of Foundation Models in Remote Sensing](https://mlsanity.com/paper/2504.17177/) (2025)
- [UNIGEOCLIP: Unified Geospatial Contrastive Learning](https://mlsanity.com/paper/2604.11668/) (2026)
- [GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?](https://mlsanity.com/paper/2505.10714/) (2025)
- [Spatial Representation Learning Beyond Pixels: Unifying Raster Data and Vector Semantics for Human-Centric Geospatial Foundation Models](https://mlsanity.com/paper/2606.02374/) (2026)
- [TrajGANR: Trajectory-Centric Urban Multimodal Learning via Geospatially Aligned Neural Representations](https://mlsanity.com/paper/2605.06990/) (2026)
- [NARA: Anchor-Conditioned Representation Learning for Heterogeneous Vector Geoentities](https://mlsanity.com/paper/2605.12276/) (2026)
- [Earth Embeddings](https://mlsanity.com/paper/2608.03410/) (2026)
- [MIND the Gap: A Geographic Implicit Neural Representation with Adjustable Spatial Scale](https://mlsanity.com/paper/2609.25454/) (2026)

## Abstract (arXiv)

Vision Transformer (ViT) has been widely used in computer vision tasks with excellent results by providing representations for a whole image or image patches. However, ViT lacks detailed localized image representations at arbitrary positions when applied to geospatial tasks that involve multiple geospatial data modalities, such as overhead remote sensing (RS) data, ground-level imagery, and geospatial vector data. Here high-resolution localized representations are vital for modeling geospatial relationships and alignments across modalities. We proposed to solve this representation problem with an implicit neural representation (INR) module extending ViT with Neural Implicit Local Interpolation, which produces a continuous RS image representation covering arbitrary location in the RS image. Based on the INR module, we introduce GAIR, a novel location-aware self-supervised learning (SSL) objective integrating overhead RS data, street view (SV) imagery, and their geolocation metadata. GAIR utilizes three factorized neural encoders to project different modalities into the embedding space, and the INR module is used to further align these representations geographically, which are trained with contrastive learning objectives from unlabeled data. We evaluate GAIR across 9 geospatial tasks and 22 datasets spanning RS image-based, SV image-based, and location embedding-based benchmarks. Experimental results demonstrate that GAIR outperforms state-of-the-art geo-foundation models (GeoFM) and alternative SSL training objectives (e.g., MoCo V3 and MAE) that do not use fine-grained geo-aligned spatial representations. Our results highlight the effectiveness of GAIR in learning generalizable geospatial representations across tasks, spatial scales, and temporal contexts. The project code is available at https://github.com/zpl99/GAIR.