GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction

• URL: http://arxiv.org/abs/2511.01082v1
• Date: Sun, 02 Nov 2025 21:30:06 GMT
• Title: GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction
• Authors: Narges Ghasemi, Amir Ziashahabi, Salman Avestimehr, Cyrus Shahabi,
• Abstract summary: We propose a hierarchical sequence prediction approach inspired by how humans narrow down locations from broad regions to specific addresses.<n>Our method uses S2 cells, a nested, multiresolution global grid, and sequentially predicts finer-level cells conditioned on visual inputs and previous predictions.<n>We evaluate our method on the Im2GPS3k and YFCC4k datasets against two distinct sets of baselines.
• Score: 23.767061975974134
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image geolocalization, the task of determining an image's geographic origin, poses significant challenges, largely due to visual similarities across disparate locations and the large search space. To address these issues, we propose a hierarchical sequence prediction approach inspired by how humans narrow down locations from broad regions to specific addresses. Analogously, our model predicts geographic tokens hierarchically, first identifying a general region and then sequentially refining predictions to increasingly precise locations. Rather than relying on explicit semantic partitions, our method uses S2 cells, a nested, multiresolution global grid, and sequentially predicts finer-level cells conditioned on visual inputs and previous predictions. This procedure mirrors autoregressive text generation in large language models. Much like in language modeling, final performance depends not only on training but also on inference-time strategy. We investigate multiple top-down traversal methods for autoregressive sampling, incorporating techniques from test-time compute scaling used in language models. Specifically, we integrate beam search and multi-sample inference while exploring various selection strategies to determine the final output. This enables the model to manage uncertainty by exploring multiple plausible paths through the hierarchy. We evaluate our method on the Im2GPS3k and YFCC4k datasets against two distinct sets of baselines: those that operate without a Multimodal Large Language Model (MLLM) and those that leverage one. In the MLLM-free setting, our model surpasses other comparable baselines on nearly all metrics, achieving state-of-the-art performance with accuracy gains of up to 13.9%. When augmented with an MLLM, our model outperforms all baselines, setting a new state-of-the-art across all metrics. The source code is available at https://github.com/NNargesNN/GeoToken.

Related papers

• Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization [26.98749852286485]
  We equip the model textitThinking with Map with agent-in-the-map loop ability and formulate it as an agent-in-the-map loop.<n>We develop a two-stage optimization scheme for it, including agentic reinforcement learning (RL) followed by parallel test-time scaling (TTS)<n>To evaluate our method on up-to-date and in-the-wild images, we further present MAPBench, a comprehensive geolocalization training and evaluation benchmark composed entirely of real-world images.
  arXiv  Detail & Related papers  (2026-01-08T23:47:30Z)
• Img2Loc: Revisiting Image Geolocalization using Multi-modality Foundation Models and Image-based Retrieval-Augmented Generation [9.161203553842787]
  We present Img2Loc, a novel system that redefines image geolocalization as a text generation task. Img2Loc first employs CLIP-based representations to generate an image-based coordinate query database. It then uniquely combines query results with images itself, forming elaborate prompts customized for LMMs. When tested on benchmark datasets such as Im2GPS3k and YFCC4k, Img2Loc not only surpasses the performance of previous state-of-the-art models but does so without any model training.
  arXiv  Detail & Related papers  (2024-03-28T17:07:02Z)
• DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control [68.14798033899955]
  Large, pretrained latent diffusion models (LDMs) have demonstrated an extraordinary ability to generate creative content. However, are they usable as large-scale data generators, e.g., to improve tasks in the perception stack, like semantic segmentation? We investigate this question in the context of autonomous driving, and answer it with a resounding "yes"
  arXiv  Detail & Related papers  (2023-12-05T18:34:12Z)
• GeoLLM: Extracting Geospatial Knowledge from Large Language Models [49.20315582673223]
  We present GeoLLM, a novel method that can effectively extract geospatial knowledge from large language models. We demonstrate the utility of our approach across multiple tasks of central interest to the international community, including the measurement of population density and economic livelihoods. Our experiments reveal that LLMs are remarkably sample-efficient, rich in geospatial information, and robust across the globe.
  arXiv  Detail & Related papers  (2023-10-10T00:03:23Z)
• AANet: Aggregation and Alignment Network with Semi-hard Positive Sample Mining for Hierarchical Place Recognition [48.043749855085025]
  Visual place recognition (VPR) is one of the research hotspots in robotics, which uses visual information to locate robots. We present a unified network capable of extracting global features for retrieving candidates via an aggregation module. We also propose a Semi-hard Positive Sample Mining (ShPSM) strategy to select appropriate hard positive images for training more robust VPR networks.
  arXiv  Detail & Related papers  (2023-10-08T14:46:11Z)
• Predicting the Geolocation of Tweets Using transformer models on Customized Data [17.55660062746406]
  This research is aimed to solve the tweet/user geolocation prediction task. The suggested approach implements neural networks for natural language processing to estimate the location. The scope of proposed models has been finetuned on a Twitter dataset.
  arXiv  Detail & Related papers  (2023-03-14T12:56:47Z)
• A Generative Language Model for Few-shot Aspect-Based Sentiment Analysis [90.24921443175514]
  We focus on aspect-based sentiment analysis, which involves extracting aspect term, category, and predicting their corresponding polarities. We propose to reformulate the extraction and prediction tasks into the sequence generation task, using a generative language model with unidirectional attention. Our approach outperforms the previous state-of-the-art (based on BERT) on average performance by a large margins in few-shot and full-shot settings.
  arXiv  Detail & Related papers  (2022-04-11T18:31:53Z)
• Scaling Structured Inference with Randomization [64.18063627155128]
  We propose a family of dynamic programming (RDP) randomized for scaling structured models to tens of thousands of latent states. Our method is widely applicable to classical DP-based inference. It is also compatible with automatic differentiation so can be integrated with neural networks seamlessly.
  arXiv  Detail & Related papers  (2021-12-07T11:26:41Z)
• Graph Sampling Based Deep Metric Learning for Generalizable Person Re-Identification [114.56752624945142]
  We argue that the most popular random sampling method, the well-known PK sampler, is not informative and efficient for deep metric learning. We propose an efficient mini batch sampling method called Graph Sampling (GS) for large-scale metric learning.
  arXiv  Detail & Related papers  (2021-04-04T06:44:15Z)
• Finding Geometric Models by Clustering in the Consensus Space [61.65661010039768]
  We propose a new algorithm for finding an unknown number of geometric models, e.g., homographies. We present a number of applications where the use of multiple geometric models improves accuracy. These include pose estimation from multiple generalized homographies; trajectory estimation of fast-moving objects.
  arXiv  Detail & Related papers  (2021-03-25T14:35:07Z)
• Learning Independent Instance Maps for Crowd Localization [44.6430092887941]
  We propose an end-to-end and straightforward framework for crowd localization, named Independent Instance Map segmentation (IIM) IIM segment crowds into independent connected components, the positions and the crowd counts are obtained. To improve the segmentation quality for different density regions, we present a differentiable Binarization Module (BM) BM brings two advantages into localization models: 1) adaptively learn a threshold map for different images to detect each instance more accurately; 2) directly train the model using loss on binary predictions and labels.
  arXiv  Detail & Related papers  (2020-12-08T02:17:19Z)
• Combining Deep Learning and String Kernels for the Localization of Swiss German Tweets [28.497747521078647]
  We address the second subtask, which targets a data set composed of nearly 30 thousand Swiss German Jodels. We frame the task as a double regression problem, employing a variety of machine learning approaches to predict both latitude and longitude. Our empirical results indicate that the handcrafted model based on string kernels outperforms the deep learning approaches.
  arXiv  Detail & Related papers  (2020-10-07T19:16:45Z)
• Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells [11.071527762096053]
  We propose a representation learning model called Space2Vec to encode the absolute positions and spatial relationships of places. Results show that because of its multi-scale representations, Space2Vec outperforms well-established ML approaches.
  arXiv  Detail & Related papers  (2020-02-16T04:22:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.