Perceptual loss guided Generative adversarial network for saliency detection
Perceptual loss guided Generative adversarial network for saliency detection
复制标题
DOI：
10.1016/j.ins.2023.119625
复制
发表时间：
2023-09
期刊：
影响因子：
--
通讯作者：
Xiaoxu Cai;Gaige Wang;Jianwen Lou;Muwei Jian;Junyu Dong;Rung-Ching Chen;Brett Stevens;Hui Yu
中科院分区：
文献类型：
--
作者：
Xiaoxu Cai;Gaige Wang;Jianwen Lou;Muwei Jian;Junyu Dong;Rung-Ching Chen;Brett Stevens;Hui Yu
在这项工作中，我们介绍了一种新的方法，通过利用感知损失引导的生成性对抗网络来检测显著。通过深度学习实现有效的显著检测需要受到多种因素影响的复杂挑战，其中损失函数的选择起着关键作用。以往的研究通常基于预测显著图和地面真实显著图之间的像素级距离来建立损失函数。然而，这些公式并没有明确地利用物体的感知属性，如它们的形状和纹理，这些属性是显著程度的关键指标。为了解决这一不足，我们提出了一种创新的损失函数，该函数利用了显著图的感知特征。我们的方法已经在六个基准数据集上进行了严格的评估，在平均绝对误差(MAE)和F度量方面与最先进的方法相比表现出了竞争的性能。值得注意的是，我们的实验显示，在使用灰度显著图或显著掩蔽的彩色图像评估知觉损失时，结果是一致的。这一观察结果强调了形状信息在塑造知觉显著线索方面的重要性。代码可在https://github.com/XiaoxuCai/PerGAN.上获得
In this work, we introduce a novel approach for saliency detection through the utilization of a generative adversarial network guided by perceptual loss. Achieving effective saliency detection through deep learning entails intricate challenges influenced by a multitude of factors, with the choice of loss function playing a pivotal role. Previous studies usually formulate loss functions based on pixel-level distances between predicted and ground-truth saliency maps. However, these formulations don’t explicitly exploit the perceptual attributes of objects, such as their shapes and textures, which serve as critical indicators of saliency. To tackle this deficiency, we propose an innovative loss function that capitalizes on perceptual features derived from the saliency map. Our approach has been rigorously evaluated on six benchmark datasets, demonstrating competitive performance when compared against the forefront methods in terms of both Mean Absolute Error (MAE) and F-measure. Remarkably, our experiments reveal consistent outcomes when assessing the perceptual loss using either grayscale saliency maps or saliency-masked colour images. This observation underscores the significance of shape information in shaping the perceptual saliency cues.The code is available at https://github.com/XiaoxuCai/PerGAN.