Improved object insertion boosts remote sensing recognition accuracy
PDA++: Field-Aligned Planning and Scene-Adaptive Insertion in Remote Sensing
Computer Vision and Pattern Recognition
Summary
Detecting rare objects in satellite images is hard because there aren't many examples and labeling is expensive. The authors created a method called PDA++ that inserts objects realistically into satellite images to make training data better. They do this by carefully planning where to place objects, adjusting the background and object to fit together, and matching textures so it looks natural. This makes computer vision models better at recognizing objects, especially when data is limited or new objects appear.
What this means in practice
- •For remote sensing analysts: Improve detection of rare or new targets in satellite imagery by augmenting training data with realistic inserted objects.
- •For maritime surveillance teams: Enhance ship detection on SAR images by generating diverse training examples even with limited real data.
Authors
Xianchi Dong, Yingyan Hou, Chao Ren, Wanxuan Lu, Zihan Wei, Hongfeng Yu, Yixiao Wang, Chubo Deng, Xian Sun
Abstract
Remote sensing recognition is often constrained by scarce observations of rare targets and costly annotations, making realistic synthetic augmentation particularly valuable for few-shot and long-tailed scenarios. Object insertion provides an efficient way to increase target diversity while preserving authentic background scenes, but realistic insertion in overhead imagery requires the generated target to adapt coherently to its surrounding environment. To this end, we propose PDA++, a unified environment-aware object insertion framework organized as Plan, Decouple, and Assimilate. Planning determines scene-compatible poses through an affordance field that combines geometric clearance with structure- and scale-aware cues. Decoupling introduces a pose-conditioned background that provides precise spatial guidance together with target-scene context, allowing the reference object to preserve its identity while adapting to the target observation. This construction also naturally provides pixel-level masks for segmentation augmentation. Assimilation further improves local coherence by aligning multi-scale texture distributions through optimal transport. On the optical benchmark, PDA++ achieves a whole-image FID of 6.28 and improves average few-shot recognition mAP50 by 17.69 points, corresponding to a 28.8% relative gain over the real-data baseline. On SAR imagery, it improves ship detection by 4.10 mAP50 points and remains effective under cross-dataset transfer and amorphous-target insertion. Code is available at https://github.com/lisheyu972/PDA_PLUS.