Category systems for real-world scenes.

Category systems for real-world scenes.
复制标题

DOI:
10.1167/jov.21.2.8
复制
发表时间:
2021-02-03
期刊:
影响因子:
1.8
通讯作者:
Adams WJ
Adams WJ
中科院分区:
医学4区
文献类型:
--
作者:
Anderson MD;Graf EW;Elder JH;Ehinger KA;Adams WJ

文献摘要

参考文献

被引文献

相似文献

分类性能是行为和计算研究中常用的场景识别和理解指标。然而,范畴构念及其标签可能有些武断。这些分类来源于详尽的地名词汇表(例如,)或一小群研究人员的判断(例如,),可能与人类喜欢的分类法不一致。在这里,我们提出了通过坐标上升(CIRCA)增加rand指数的聚类方法:一种无监督的、数据驱动的聚类方法,用于导出地面真实场景类别。在实验1中,人类参与者将来自南安普敦-约克自然场景(SYNS)数据集的80幅户外场景立体图像组织到离散的类别中。在单独的任务中,根据i)语义内容,ii)三维空间结构或iii)二维图像外观对图像进行分组。参与者为每一组提供文本标签。使用CIRCA方法,我们确定了最具代表性的类别结构,然后为每个任务/维度导出了类别标签。在实验2中,我们发现这些类别可以很好地推广到更大的syn图像集和新的观察者。在实验3中,我们测试了我们的类别系统与空间包络模型之间的关系。最后,在实验4中,我们在一个更大的相同-不同类别判断的独立数据集上验证了CIRCA。派生的类别系统优于SUN分类法和另一种聚类方法。总之,我们相信这种新的分类方法可以应用于广泛的数据集,从刺激相似性的心理物理判断中获得最佳的分类分组和标签。
Categorization performance is a popular metric of scene recognition and understanding in behavioral and computational research. However, categorical constructs and their labels can be somewhat arbitrary. Derived from exhaustive vocabularies of place names (e.g.,), or the judgements of small groups of researchers (e.g.,), these categories may not correspond with human-preferred taxonomies. Here, we propose clustering by increasing the rand index via coordinate ascent (CIRCA): an unsupervised, data-driven clustering method for deriving ground-truth scene categories. In Experiment 1, human participants organized 80 stereoscopic images of outdoor scenes from the Southampton-York Natural Scenes (SYNS) dataset into discrete categories. In separate tasks, images were grouped according to i) semantic content, ii) three-dimensional spatial structure, or iii) two-dimensional image appearance. Participants provided text labels for each group. Using the CIRCA method, we determined the most representative category structure and then derived category labels for each task/dimension. In Experiment 2, we found that these categories generalized well to a larger set of SYNS images, and new observers. In Experiment 3, we tested the relationship between our category systems and the spatial envelope model. Finally, in Experiment 4, we validated CIRCA on a larger, independent dataset of same-different category judgements. The derived category systems outperformed the SUN taxonomy and an alternative clustering method. In summary, we believe this novel categorization method can be applied to a wide range of datasets to derive optimal categorical groupings and labels from psychophysical judgements of stimulus similarity.
DOI: 10.1016/s0364-0213(03)00002-8
发表时间: 2003-03-01
期刊: COGNITIVE SCIENCE
影响因子: 2.5
作者:
Goffaux, V;Jemel, B;Schyns, PG
通讯作者: Schyns, PG
DOI: 10.1364/josaa.5.001749
发表时间: 1988-10-01
影响因子: 1.9
作者:
BULTHOFF, HH;MALLOT, HA
通讯作者: MALLOT, HA
DOI: 10.1523/jneurosci.5111-14.2015
发表时间: 2015-06-24
影响因子: 5.3
作者:
Boutonnet, Bastien;Lupyan, Gary
通讯作者: Lupyan, Gary
触摸会影响感知的光泽。
DOI: 10.1038/srep21866
发表时间: 2016-02-26
期刊: Scientific reports
影响因子: 4.6
作者:
Adams WJ;Kerrigan IS;Graf EW
通讯作者: Graf EW
DOI: 10.1068/p5445
发表时间: 2006-01-01
期刊: PERCEPTION
影响因子: 1.7
作者:
Collin, CA
通讯作者: Collin, CA