arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.07807cs.CVcs.AIq-bio.NC
收藏

人类视觉分割中的不确定性测量

Measuring uncertainty in human visual segmentation

École normale supérieure, PSL University(巴黎高等师范学院,PSL大学);CNRS(法国国家科学研究中心);Albert Einstein College of Medicine(阿尔伯特·爱因斯坦医学院);Université Paris Cité(巴黎西岱大学)

Jonathan Vacher, Claire Launay, Pascal Mamassian, Ruben Coen-Cagli

AI总结:

提出一种集成方法,通过像素级相同-不同判断和模型重建测量人类视觉分割图,验证于自然图像与复合纹理,揭示图像不确定性影响人类变异性与特征权衡,为感知理论和分割算法提供定量测试与基准。

摘要:

将视觉刺激分割为不同的特征组和视觉对象是视觉功能的核心。经典心理物理学方法已帮助揭示人类感知分割的许多规则,而机器学习的最新进展也产生了成功的算法。然而,人类分割的计算逻辑仍不清楚,部分原因在于我们缺乏受控良好的范式来测量感知分割图并定量比较模型。在此,我们提出一种新的集成方法:给定一幅图像,我们测量多个基于像素的相同-不同判断,并执行基于模型的分割图重建。该重建对若干实验操作具有鲁棒性,并能捕捉个体参与者的变异性。我们在自然图像和复合纹理的人类分割中展示了该方法的有效性。我们表明,图像不确定性影响所测量的人类变异性,并影响参与者如何权衡不同的视觉特征。由于任何假定的分割算法都可以插入以执行重建,我们的范式为感知理论提供了定量测试,也为分割算法提供了新的基准。

英文摘要:

Segmenting visual stimuli into distinct groups of features and visual objects is central to visual function. Classical psychophysical methods have helped uncover many rules of human perceptual segmentation, and recent progress in machine learning has produced successful algorithms. Yet, the computational logic of human segmentation remains unclear, partially because we lack well-controlled paradigms to measure perceptual segmentation maps and compare models quantitatively. Here we propose a new, integrated approach: given an image, we measure multiple pixel-based same--different judgments and perform model--based reconstruction of the underlying segmentation map. The reconstruction is robust to several experimental manipulations and captures the variability of individual participants. We demonstrate the validity of the approach on human segmentation of natural images and composite textures. We show that image uncertainty affects measured human variability, and it influences how participants weigh different visual features. Because any putative segmentation algorithm can be inserted to perform the reconstruction, our paradigm affords quantitative tests of theories of perception as well as new benchmarks for segmentation algorithms.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑