arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2005.12073cs.CVcs.LGeess.IV
收藏

视觉注意:深稀有特征

Visual Attention: Deep Rare Features

University of Mons(蒙斯大学);Institute of Technology of Cambodia(柬埔寨理工学院)

Matei Mancas, Phutphalla Kong, Bernard Gosselin

摘要:

人类视觉系统在工程领域中被建模,提供特征工程方法,将对比/令人惊讶/不寻常的数据检测到图像中。这些数据对人类来说是“有趣的”,并导致了许多应用。深度学习(DNN)极大地提高了算法在主要基准数据集上的效率。然而,基于DNN的模型是违反直觉的:令人惊讶或不寻常的数据由于其发生概率低而难以学习。实际上,DNN模型主要学习自上而下的特征,如人脸、文本、人或动物,这些特征通常会引起人类的注意,但它们在提取图像中令人惊讶或不寻常的数据时效率很低。在本文中,我们提出了一个名为DeepRare 2019(DR)的模型,该模型利用了DNN特征提取的强大功能和特征工程算法的通用性。DR 1)不需要任何训练,2)仅在CPU上每张图像的时间不到一秒,3)我们对三个非常不同的眼动跟踪数据集的测试表明,DR是通用的,并且总是在所有数据集和指标上的前三个模型中,而没有其他模型表现出这样的规律性和通用性。DeepRare 2019代码可以在https://github.com/numediart/VisualAttention-RareFamily上找到

英文摘要:

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

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。

↑