UHR-BAT: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing
Yunkai Dang, Minxin Dai, Yuekun Yang, Zhangnanli, Wenbin Li, Feng Miao, Yang Gao
Abstract
Ultra-high-resolution (UHR) remote sensing imagery couples kilometer-scale context with query-critical evidence that may occupy only a few pixels. Such vast spatial scale leads to a quadratic explosion of visual tokens and hinders the extraction of information from small objects. Previous works utilize direct downsampling, dense tiling, or global top‑K pruning, which either compromise query-critical image details or incur unpredictable compute. In this paper, we propose UHR-BAT, a query-guided and region-faithful token compression framework to efficiently select visual tokens under strict context budget. Specifically, we leverage text-guided, multi-scale importance estimation for visual tokens, effectively tackling the challenge of achieving precise yet low-cost feature extraction. Furthermore, by introducing region-wise preserve and merge strategies, we mitigate visual token redundancy, further driving down the computational budget. The experimental results show that UHR-BAT achieves state-of-the-art performance across various benchmarks.
BibTeX
@inproceedings{
dang2026uhrbat,
title={{UHR}-{BAT}: Budget-Aware Token Compression Vision-Language model for Ultra-High-Resolution Remote Sensing},
author={Yunkai Dang and Minxin Dai and Yuekun Yang and Zhangnan Li and Wenbin Li and Feng Miao and Yang Gao},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=AWPKhE1dbc}
}