In this work we consider the task of relaxing the i.i.d assumption in pattern recognition (or classification), aiming to make existing learning algorithms applicable to a wider range of tasks. Pattern recognition is guessing a discrete label of some object based on a set of given examples (pairs of objects and labels). We consider the case of deterministically defined labels. Traditionally, this task is studied under the assumption that examples are independent and identically distributed. However, it turns out that many results of pattern recognition theory carry over a weaker assumption. Namely, under the assumption of conditional independence and identical distribution of objects, while the only assumption on the distribution of labels is that the rate of occurrence of each label should be above some positive threshold.
We find a broad class of learning algorithms for which estimations of the probability of a classification error achieved under the classical i.i.d. assumption can be generalised to the similar estimates for the case of conditionally i.i.d. examples.
Conditionally Learn to Pay Attention for Sequential Visual Task
Nanjing University of Information Science and Technology(南京信息工程大学);Nanjing Normal University(南京师范大学)
顺序视觉任务通常要求在先前观察的基础上注意当前感兴趣的对象。与目前流行的软注意力机制不同,本文提出了一种新的注意力框架,通过引入一种新的条件全局特征来表示当前关注对象的弱特征描述符。具体而言,对于标准CNN(卷积神经网络)流水线,具有不同感受野的卷积层用于通过测量卷积特征如何与条件全局特征对齐来产生注意力图。条件全局特征可以根据不同的视觉任务采用不同的递归结构生成,如简单的递归神经网络用于多目标识别,或适度复杂的语言模型用于图像字幕。实验结果表明,在SVHN(Street View House Numbers)数据集上,无论是否有额外的限界框,我们提出的条件注意力模型都取得了最好的性能;对于图像标题,我们的注意力模型都比流行的软注意力模型产生更好的分数。
Electricité De France R&D(法国电力公司研发部);INRIA(法国国家信息与自动化研究所);CNRS(法国国家科学研究中心);École polytechnique(巴黎综合理工学院);Institut Polytechnique de Paris(巴黎理工学院);Technion - Israel Institute of Technology(以色列理工学院)
A Rapid Pattern-Recognition Method for Driving Types Using Clustering-Based Support Vector Machines
Beijing Institute of Technology(北京理工大学);UC Berkeley(加州大学伯克利分校)
提出了一种快速模式识别方法来表征驾驶员曲线通过行为。为了缩短识别时间,提高驾驶风格的识别率,提出了一种基于k均值聚类的支持向量机(kMC-SVM)方法,并将其用于驾驶员的驾驶风格分类。首先将车速和节气门开度作为反映驾驶风格的特征参数。其次,为了区分驾驶员曲线通过行为,减少支持向量的数量,采用k-均值聚类方法对两类驾驶数据进行提取和聚类,缩短识别时间。然后,基于聚类结果,利用支持向量机方法生成超平面,用于判断和预测人类驾驶员属于哪种类型。最后,为了验证kMC-SVM方法的有效性,设计并进行了交叉验证实验。研究结果表明,与SVM方法相比,$ k $ MC-SVM方法是一种有效的驾驶风格分类方法,分类时间短。