当前位置: X-MOL 学术Pattern Recogn. Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Saliency for free: Saliency prediction as a side-effect of object recognition
Pattern Recognition Letters ( IF 5.1 ) Pub Date : 2021-07-08 , DOI: 10.1016/j.patrec.2021.05.015
Carola Figueroa-Flores 1, 2 , David Berga 1 , Joost van de Weijer 1 , Bogdan Raducanu 1
Affiliation  

Saliency is the perceptual capacity of our visual system to focus our attention (i.e. gaze) on relevant objects instead of the background. So far, computational methods for saliency estimation required the explicit generation of a saliency map, process which is usually achieved via eyetracking experiments on still images. This is a tedious process that needs to be repeated for each new dataset. In the current paper, we demonstrate that is possible to automatically generate saliency maps without ground-truth. In our approach, saliency maps are learned as a side effect of object recognition. Extensive experiments carried out on both real and synthetic datasets demonstrated that our approach is able to generate accurate saliency maps, achieving competitive results when compared with supervised methods.



中文翻译:

免费显着性:作为对象识别副作用的显着性预测

显着性是我们的视觉系统将我们的注意力(即注视)集中在相关对象而不是背景上的感知能力。到目前为止,显着性估计的计算方法需要显式生成显着性图,该过程通常通过对静止图像进行眼动追踪实验来实现。这是一个繁琐的过程,需要为每个新数据集重复。在当前的论文中,我们证明了可以在没有地面实况的情况下自动生成显着图。在我们的方法中,显着图是作为对象识别的副作用来学习的。在真实和合成数据集上进行的大量实验表明,与监督方法相比,我们的方法能够生成准确的显着图,取得有竞争力的结果。

更新日期:2021-07-16
down
wechat
bug