Diverse Instance Generation via Diffusion Models for Enhanced Few-Shot Object Detection in Remote Sensing Images

TL;DR

This paper introduces a diffusion model-based data augmentation framework that synthesizes diverse remote sensing instances at the slice level, significantly improving few-shot object detection performance in remote sensing images.

Contribution

The authors propose a novel diffusion model approach with slice-to-slice synthesis and semantic inversion modules tailored for remote sensing, enhancing diversity and detection accuracy in few-shot scenarios.

Findings

Achieved an average of 4.4% performance improvement across datasets.

The inversion module effectively enhances FSOD performance.

Semantic contrastive loss further boosts detection accuracy.

Abstract

Few-shot object detection (FSOD) aims to detect novel instances with only a limited number of labeled training samples, presenting a challenge that is particularly prominent in numerous remote sensing applications such as endangered species monitoring and disaster assessment. Existing FSOD methods for remote sensing images (RSIs) have achieved promising progress but remain constrained by the limited diversity of instances. To address this issue, we propose a novel framework that can leverage a diffusion model pretrained on large-scale natural images to synthesize diverse remote sensing instances, thereby improving the performance of few-shot object detectors. Instead of directly synthesizing complete remote sensing images, we first generate instance-level slices via a specialized slice-to-slice module, and then embed these slices into full-scale imagery for enhanced data augmentation. To further adapt diffusion models for remote sensing scenarios, we develop a class-agnostic image inversion module that can invert remote sensing instance slices into semantic space. Additionally, we introduce contrastive loss to semantically align the synthesized images with their corresponding classes. Experimental results show that our method hasachieved an average performance improvement of 4.4% across multiple datasets and various approaches. Ablation experiments indicate that the elaborately designed inversion module can effectively enhance the performance of FSOD methods, and the semantic contrastive loss can further boost the performance.