Hierarchical Fine-Grained Aerial Object Detection

2026-06-15

AI Summary

Existing aerial object detection methods struggle to distinguish fine-grained model categories due to their reliance on single-label supervision, which fails to capture subtle structural differences. To address this limitation, this work proposes Visual-aware Mask Attribute Modeling (VMAM) and a Hierarchical Visual Instance Promotion mechanism (HierVIP), which for the first time incorporate expert prior knowledge into fine-grained modeling. By aligning attribute semantics with visual structures and constructing a category-hierarchical visual prototype tree, the approach enhances semantic continuity and class discriminability across multiple granularities. Additionally, the authors introduce PSP, the most comprehensive benchmark to date for model-level aerial object detection, encompassing 106 ship classes and 30 aircraft models. Experiments demonstrate that the proposed method significantly outperforms existing approaches on PSP, achieving substantial improvements in cross-hierarchical fine-grained detection performance.

Abstract

Fine-grained aerial object detection, driven by the intrinsic granularity of real-world object categories, is crucial for advanced scene understanding in remote sensing. Existing methods largely inherit the paradigm of coarse-grained object detection, relying solely on single-label supervision and thus struggling to distinguish model-level categories with subtle structural differences. However, for each specific model (e.g., Boeing 787), structured prior knowledge such as attributes and hierarchies offers discriminative semantics across multiple granularities. Motivated by this, we present ExpertDet, a scheme that incorporates expert-informed cues to enhance fine-grained aerial object detection. Specifically, we design Vision-aware Masked Attribute Modeling (VMAM), which aligns attribute semantics with visual structures by reconstructing randomly masked attributes from visual cues, enabling the detector to capture subtle structural distinctions. We further propose Hierarchical Visual Instance Promotion (HierVIP), which builds a visual prototype tree based on hierarchical relations and imposes taxonomy-aware constraints to preserve cross-level semantic continuity while enhancing category discrimination. Moreover, we curate a new fine-grained object detection benchmark for Precise recognition of model-specific Ships and Planes from aerial imagery, PSP, covering 106 ship classes and 30 airplane models, respectively, featuring the most extensive collection of model-specific categories among existing aerial object detection datasets to date. We benchmark state-of-the-art object detection algorithms on the PSP benchmark. Extensive evaluation demonstrates that ExpertDet consistently outperforms other fine-grained competitors across hierarchy levels. The dataset, benchmark, and code are available at https://nnnnerd.github.io/PSP-Benchmark/.

Problem

• fine-grained aerial object detection
• model-level categorization
• hierarchical semantics
• attribute-aware recognition
• remote sensing

Innovation

• fine-grained aerial object detection
• Vision-aware Masked Attribute Modeling
• Hierarchical Visual Instance Promotion
• expert-informed cues
• hierarchical prototype tree