MTMS300: a multiple-targets and multiple-scales benchmark dataset for salient object detection

During the development of salient object detection algorithms, benchmark datasets have played a critical role. However, existing benchmark datasets commonly suffer from dataset bias, making it challenging to fully reflect the performance of different algorithms or capture the technical characteristics of certain typical applications. To address these limitations, we have undertaken two key initiatives: (1) We designed a new benchmark dataset, MTMS300 (Multiple Targets and Multiple Scales), tailored to reconnaissance and surveillance applications. This dataset contains 300 color visible-light images from land, sea, and air scenarios, featuring: Reduced center bias, Balanced distribution of target-to-image area ratios, Diverse image sizes, Multiple targets per image.(2) We curated a new benchmark dataset, DSC (Difficult Scenes in Common), by identifying images from publicly available benchmarks that pose significant challenges (with low metric scores) for most non-deep-learning algorithms. The proposed datasets exhibit distinct characteristics, enabling more comprehensive evaluation of visual saliency algorithms. This advancement will drive the development of visual saliency algorithms toward task-specific applications.

在显著目标检测算法的研发进程中，基准数据集扮演着关键角色。然而，现有基准数据集普遍存在数据集偏差问题，导致难以全面反映不同算法的性能，或捕捉某些典型应用的技术特征。为解决这些局限，我们采取了两项核心举措：（1）针对侦察与监视应用，设计了全新的基准数据集MTMS300（Multiple Targets and Multiple Scales，多目标多尺度）。该数据集包含300张来自陆、海、空场景的彩色可见光图像，具有以下特点：降低的中心偏差、目标与图像面积比的均衡分布、多样的图像尺寸、每张图像含多个目标；（2）通过识别公开基准中对大多数非深度学习算法构成显著挑战（即metric得分较低）的图像，构建了新的基准数据集DSC（Difficult Scenes in Common，常见困难场景）。所提出的数据集具有独特特征，能够更全面地评估视觉显著性算法。这一进展将推动视觉显著性算法向任务特定的应用方向发展。