用确定性流生成方法提升遥感图像显著目标检测精度与速度
ORSIFlow: Saliency-Guided Rectified Flow for Optical Remote Sensing Salient Object Detection
- 将显著目标检测转为确定性潜在空间流动生成，避免随机采样
- 在多个公开数据集上达到顶尖性能，推理仅需少数步骤
- 适合需要高效高精度遥感图像分析的研究与应用
光学遥感图像显著目标检测（ORSI-SOD）因背景复杂、对比度低、目标形状不规则及尺度变化大而具有挑战性。现有判别式方法直接回归显著图，而基于扩散的生成方法存在随机采样和高计算开销问题。本文提出 ORSIFlow，一种基于显著性引导的修正流框架，将 ORSI-SOD 重构为确定性的潜在流生成问题。ORSIFlow 在由冻结变分自编码器构建的紧凑潜在空间中生成显著掩码，实现仅需少数步骤的高效推理。为增强显著性感知，设计了全局语义判别器与边界精修校准器。在多个公开基准上的大量实验表明，ORSIFlow 在显著提升性能的同时，效率大幅优化。
原文摘要 · Abstract (English)
Optical Remote Sensing Image Salient Object Detection (ORSI-SOD) remains challenging due to complex backgrounds, low contrast, irregular object shapes, and large variations in object scale. Existing discriminative methods directly regress saliency maps, while recent diffusion-based generative approaches suffer from stochastic sampling and high computational cost. In this paper, we propose ORSIFlow, a saliency-guided rectified flow framework that reformulates ORSI-SOD as a deterministic latent flow generation problem. ORSIFlow performs saliency mask generation in a compact latent space constructed by a frozen variational autoencoder, enabling efficient inference with only a few steps. To enhance saliency awareness, we design a Salient Feature Discriminator for global semantic discrimination and a Salient Feature Calibrator for precise boundary refinement. Extensive experiments on multiple public benchmarks show that ORSIFlow achieves state-of-the-art performance with significantly improved efficiency.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。