论文标题
显着性模型是否检测到奇怪的目标？新数据集和评估
Do Saliency Models Detect Odd-One-Out Targets? New Datasets and Evaluations
论文作者
论文摘要
显着性领域的最新进展集中在固定预测上，基准达到饱和。但是，心理学和神经科学方面有广泛的作品描述了人类视觉关注的各个方面，而当前方法可能无法充分捕捉。在这里，我们研究了单例检测，可以将其视为显着性的规范例子。我们介绍了两个新型数据集，一个数据集具有心理物理模式，一个具有自然的奇数刺激。使用这些数据集，我们通过广泛的实验证明，几乎所有显着性算法都不能充分响应合成和自然图像中的单例目标。此外，我们研究了训练最先进的CNN显着性模型对这些类型刺激的影响，并得出结论，额外的训练数据不会显着提高其找到奇怪的目标的能力。数据集可在http://data.nvision2.eecs.yorku.ca/p3o3/上找到。
Recent advances in the field of saliency have concentrated on fixation prediction, with benchmarks reaching saturation. However, there is an extensive body of works in psychology and neuroscience that describe aspects of human visual attention that might not be adequately captured by current approaches. Here, we investigate singleton detection, which can be thought of as a canonical example of salience. We introduce two novel datasets, one with psychophysical patterns and one with natural odd-one-out stimuli. Using these datasets we demonstrate through extensive experimentation that nearly all saliency algorithms do not adequately respond to singleton targets in synthetic and natural images. Furthermore, we investigate the effect of training state-of-the-art CNN-based saliency models on these types of stimuli and conclude that the additional training data does not lead to a significant improvement of their ability to find odd-one-out targets. Datasets are available at http://data.nvision2.eecs.yorku.ca/P3O3/.
