arXiv cs.AI· Jisheng Dang, Huaiyuan Peng, Yixuan Wang, Kun Wang, Zhang Li, Tat-Seng Chua·· 15 小时前AI 评分31
Aerial-R1：强化 MLLM 的空中推理与分割能力
Aerial-R1: Reinforcing Aerial Reasoning and Segmentation in MLLMs
AI 导读
Aerial-R1 是首个面向空中场景强化视觉推理与分割能力的 MLLM 框架，借鉴 DeepSeek-R1 的推理激励机制，提出 H-GAWR 策略，通过构建高/低分辨率视图动态分组，将组相对优势估计与优势加权策略提取结合，并形成显式拒绝机制。在首个空中 MLLM 基准 VSAI-Ref 上，Aerial-R1 的分割精度显著优于 SFT 基线，同时大幅减少低信息场景下的致命幻觉。代码已公开。
正文 · 原文
Abstract:While Multimodal Large Language Models (MLLMs) have revolutionized general visual perception, existing methods suffer from severe hallucination in the aerial domain, where extreme scale variations and visual ambiguity abound. Existing Supervised Fine-Tuning (SFT) paradigms force models to mimic ground truth without modeling uncertainty, often resulting in blind guessing on tiny or unrecognizable objects in aerial scenes. In this paper, we present Aerial-R1, the first aerial MLLM framework to reinforce visual reasoning capabilities for aerial reasoning and segmentation. Drawing inspiration from the reasoning-incentivizing mechanisms of DeepSeek-R1, we find that trustworthy perception stems from consistency across views, establishing a visual parallel to the Chain-of-Thought in logic. To effectively adapt policy optimization for non-autoregressive mask generation, we introduce Hybrid-View Group Advantage-Weighted Regression (H-GAWR). This strategy constructs dynamic groups of high-resolution and low-resolution views, seamlessly bridging group-relative advantage estimation with advantage-weighted policy extraction. By enforcing consensus on clear inputs and strictly penalizing hallucinations on ambiguous ones, Aerial-R1 develops an explicitly incentivized refusal mechanism. Extensive experiments on VSAI-Ref, the first aerial MLLM benchmark dedicated to jointly evaluating dense reasoning and hallucination robustness, demonstrate that Aerial-R1 significantly outperforms SFT baselines in segmentation precision while substantially mitigating fatal hallucinations in low-information scenarios, paving the way for more reliable and trustworthy aerial agents. Codes are available on this https URL.
| Comments: | 16 pages, 8 figures, including supplementary material |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.33056 [cs.CV] |
| (or arXiv:2610.33056v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33056 arXiv-issued DOI via DataCite |
Submission history
From: Huaiyuan Peng [view email]
[v1]
Mon, 19 Oct 2026 08:44:04 UTC (3,395 KB)
来源：arXiv cs.AI · arxiv.org