# GATA2Floor: Graph attention for floor counting in street-view facades

arXiv: https://arxiv.org/abs/2605.11863 · HTML: https://mlsanity.com/paper/2605.11863/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 12 May 2026.

## Builds on (most cited first, 14 of 14)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [How Attentive are Graph Attention Networks?](https://mlsanity.com/paper/2105.14491/) (2021)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [Semi-supervised Learning from Street-View Images and OpenStreetMap for Automatic Building Height Estimation](https://mlsanity.com/paper/2307.02574/) (2023)
- [Zero-shot Building Attribute Extraction from Large-Scale Vision and Language Models](https://mlsanity.com/paper/2312.12479/) (2023)
- [FloorLevel-Net: Recognizing Floor-Level Lines with Height-Attention-Guided Multi-task Learning](https://mlsanity.com/paper/2107.02462/) (2021)
- [Building Floor Number Estimation from Crowdsourced Street-Level Images: Munich Dataset and Baseline Method](https://mlsanity.com/paper/2505.18021/) (2025)

## Abstract (arXiv)

Automated analysis of building facades from street-level imagery has great potential for urban analytics, energy assessment, and emergency planning. However, it requires reasoning over spatially arranged elements rather than solely isolated detections. In this work, we model each facade as a graph over window/door detections with a vertical prior on edges. Additionally, we introduce GATA2Floor, a multi-head Graph Attention v2 (GATv2) based model that predicts the global floor count of a building and, via learnable cross-attention queries, softly assigns elements to latent floor slots, yielding interpretable outputs and robustness to irregular designs. To mitigate the lack of labeled datasets, we demonstrate that the proposed graph-based reasoning can be applied without annotations by leveraging a lightweight label-free proposal mechanism based on self-supervised features and vision-language scoring. Our approach demonstrates the value of graph-attention-based relational reasoning for facade understanding.