Control Copy-Paste: Controllable Diffusion-Based Augmentation Method for Remote Sensing Few-Shot Object Detection

TL;DR

This paper introduces Control Copy-Paste, a diffusion-based augmentation method that improves remote sensing few-shot object detection by controllably inserting diverse objects and contexts, reducing overfitting and enhancing detection accuracy.

Contribution

The paper presents a novel controllable diffusion-based augmentation technique that effectively incorporates diverse objects and contexts for improved FSOD in remote sensing images.

Findings

Achieved an average 10.76% improvement in detection performance on DIOR dataset.

Effectively mitigated overfitting by enhancing data diversity with diffusion models.

Developed an orientation alignment strategy to reduce integration distortion.

Abstract

Few-shot object detection (FSOD) for optical remote sensing images aims to detect rare objects with only a few annotated bounding boxes. The limited training data makes it difficult to represent the data distribution of realistic remote sensing scenes, which results in the notorious overfitting problem. Current researchers have begun to enhance the diversity of few-shot novel instances by leveraging diffusion models to solve the overfitting problem. However, naively increasing the diversity of objects is insufficient, as surrounding contexts also play a crucial role in object detection, and in cases where the object diversity is sufficient, the detector tends to overfit to monotonous contexts. Accordingly, we propose Control Copy-Paste, a controllable diffusion-based method to enhance the performance of FSOD by leveraging diverse contextual information. Specifically, we seamlessly inject a few-shot novel objects into images with diverse contexts by a conditional diffusion model. We also develop an orientation alignment strategy to mitigate the integration distortion caused by varying aspect ratios of instances. Experiments on the public DIOR dataset demonstrate that our method can improve detection performance by an average of 10.76%.