Abstract
This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at this https URL.
Abstract (translated)
本文探讨了在显著物体检测(SOD)中评估指标的大小不变性,特别是在同一图像中存在多种大小不同的目标时。我们观察到,当前的指标对大小敏感,较大的目标被集中,而较小的目标则往往被忽略。我们认为,评估应该是大小不变的,因为基于大小的偏见在没有额外语义信息的情况下是不公正的。为了实现这一目标,我们提出了一个通用方法,对每个显著物体进行单独评估,然后将结果进行组合,有效地减轻了不平衡。我们进一步开发了一个针对这一目标的优化框架,在检测不同大小的物体方面取得了显著的改进。从理论上讲,我们提供了支持我们新指标有效性的证据,并研究了SOD的泛化分析。大量实验证实了我们的方法的的有效性。代码可在此处访问:https://url.cn/xyz0wx
URL
https://arxiv.org/abs/2405.09782