Attention Guided Network for Salient Object Detection in Optical Remote Sensing Images

TL;DR

This paper introduces AGNet, an attention-guided neural network designed specifically for salient object detection in optical remote sensing images, addressing challenges posed by complex scale, shape, and location uncertainty.

Contribution

The paper presents a novel AGNet architecture with position enhancement and detail refinement stages, tailored for remote sensing images, and introduces a hybrid loss for improved training.

Findings

AGNet achieves competitive results on benchmark datasets.

The attention modules effectively locate salient objects in complex images.

Hybrid loss improves detection accuracy from multiple perspectives.

Abstract

Due to the extreme complexity of scale and shape as well as the uncertainty of the predicted location, salient object detection in optical remote sensing images (RSI-SOD) is a very difficult task. The existing SOD methods can satisfy the detection performance for natural scene images, but they are not well adapted to RSI-SOD due to the above-mentioned image characteristics in remote sensing images. In this paper, we propose a novel Attention Guided Network (AGNet) for SOD in optical RSIs, including position enhancement stage and detail refinement stage. Specifically, the position enhancement stage consists of a semantic attention module and a contextual attention module to accurately describe the approximate location of salient objects. The detail refinement stage uses the proposed self-refinement module to progressively refine the predicted results under the guidance of attention and reverse attention. In addition, the hybrid loss is applied to supervise the training of the network, which can improve the performance of the model from three perspectives of pixel, region and statistics. Extensive experiments on two popular benchmarks demonstrate that AGNet achieves competitive performance compared to other state-of-the-art methods. The code will be available at https://github.com/NuaaYH/AGNet.