Data Augmentation Method Based on Context-Aware Patch for Remote Sensing Object Detection

Abstract

Object detection in aerial imagery has garnered significant attention due to its crucial role in applications such as urban planning, environmental monitoring, and disaster response. However, class imbalance remains a persistent challenge, as minority categories are represented by fewer instances than dominant classes in most remote-sensing datasets. To address this issue, we propose a novel context-aware patch (CAP)-based data augmentation method that mitigates class imbalance by selectively choosing donor images and semantically compatible object instances. The proposed method features two key innovations. First, it preserves contextual coherence by leveraging class-specific donor collections and enforcing geometric and semantic constraints (e.g., boundary, shape, and class). Second, it introduces a class-balancing threshold computed from dataset statistics to dynamically regulate augmentation copy–paste probability for minority categories. We evaluate the approach on DOTA-v1.0, demonstrating a significant improvement in mAP@0.5 and mAP@0.5–0.95 for minority categories while preserving competitive performance for majority classes.