论文标题
视觉关注：稀有功能
Visual Attention: Deep Rare Features
论文作者
论文摘要
人类视觉系统在工程领域建模，提供了特征工程的方法，这些方法将对比/令人惊讶/异常数据中的图像中的图像进行建模。这些数据对于人类来说是“有趣的”，并且导致了许多应用。深度学习（DNN）大大提高了主要基准数据集的算法效率。但是，基于DNN的模型是违反直觉的：从定义上讲，令人惊讶或不寻常的数据由于其出现概率很低而难以学习。实际上，DNNS模型主要学习自上而下的功能，例如通常吸引人类注意力的面部，文字，人或动物，但在图像中提取令人惊讶或异常数据方面的效率较低。在本文中，我们提出了一个称为DeepRare2019（DR）的模型，该模型使用DNNS功能提取和特征工程算法的通用性。 DR 1）不需要任何培训，2）仅在CPU上的每个图像不到一秒钟，而3）我们在三个非常不同的眼睛跟踪数据集上的测试表明，DR是通用的，并且在所有数据集和指标上始终处于前3个模型中，而没有其他模型则表现出规律性和一般性。 DeepRare2019代码可以在https://github.com/numediart/visualatterention-rarefamily上找到
Human visual system is modeled in engineering field providing feature-engineered methods which detect contrasted/surprising/unusual data into images. This data is "interesting" for humans and leads to numerous applications. Deep learning (DNNs) drastically improved the algorithms efficiency on the main benchmark datasets. However, DNN-based models are counter-intuitive: surprising or unusual data is by definition difficult to learn because of its low occurrence probability. In reality, DNNs models mainly learn top-down features such as faces, text, people, or animals which usually attract human attention, but they have low efficiency in extracting surprising or unusual data in the images. In this paper, we propose a model called DeepRare2019 (DR) which uses the power of DNNs feature extraction and the genericity of feature-engineered algorithms. DR 1) does not need any training, 2) it takes less than a second per image on CPU only and 3) our tests on three very different eye-tracking datasets show that DR is generic and is always in the top-3 models on all datasets and metrics while no other model exhibits such a regularity and genericity. DeepRare2019 code can be found at https://github.com/numediart/VisualAttention-RareFamily
