# What Does CLIP Learn for Regional Geolocalization? Probing Visual Cues and Scene Configuration After Adaptation

arXiv: https://arxiv.org/abs/2608.21761 · HTML: https://mlsanity.com/paper/2608.21761/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 29 references that are in the map.
- First posted on arXiv 22 Aug 2026.

## Builds on (most cited first, 18 of 18)

- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [A Benchmark for Interpretability Methods in Deep Neural Networks](https://mlsanity.com/paper/1806.10758/) (2018)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization](https://mlsanity.com/paper/2309.16020/) (2023)
- [PlaNet - Photo Geolocation with Convolutional Neural Networks](https://mlsanity.com/paper/1602.05314/) (2016)
- [Revisiting IM2GPS in the Deep Learning Era](https://mlsanity.com/paper/1705.04838/) (2017)
- [PIGEON: Predicting Image Geolocations](https://mlsanity.com/paper/2307.05845/) (2023)
- [Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization](https://mlsanity.com/paper/2302.00275/) (2023)
- [OpenStreetView-5M: The Many Roads to Global Visual Geolocation](https://mlsanity.com/paper/2404.18873/) (2024)
- [AddressCLIP: Empowering Vision-Language Models for City-wide Image Address Localization](https://mlsanity.com/paper/2407.08156/) (2024)

## Abstract (arXiv)

Large collections of street-view imagery provide rich visual information about urban environments, but extracting fine-grained geographic information from such data remains challenging. In particular, fine-grained regional geolocalization is challenging because nearby areas often share coarse geographic cues. We study regional geolocalization within a metropolitan area and ask whether pretrained CLIP features are sufficient for regional discrimination, and what visual information supports performance after adaptation. Using 9,085 street-view images from eight Greater Los Angeles regions, we compare zero-shot CLIP, frozen-encoder readouts, partial encoder updating, Low-Rank Adaptation (LoRA), and full fine-tuning. Frozen readouts remain near the 39.03% zero-shot accuracy, whereas encoder adaptation achieves 75.94-82.10%. Full fine-tuning also reduces the mean distance to the predicted region center from 12.30 km to 3.86 km. We probe these gains through semantic cue removal, appearance reduction using edge maps and blur, and scene-configuration disruption using patch scrambling. Adapted models achieve higher edge and blur accuracy and switch 42.92-45.56% of predictions after scrambling, compared with 10.79-14.60% for frozen methods. However, adaptation does not improve the fraction of performance retained after appearance reduction, while vegetation and sky remain influential. A Caltech101 control further shows that scrambling sensitivity is not unique to geolocalization. Overall, encoder adaptation substantially improves nearby-region discrimination and is associated with greater sensitivity to intact scene configuration, without evidence that coarse structure alone becomes sufficient for prediction. These conclusions concern viewpoint variation near known locations rather than geographically disjoint generalization.