当前位置: X-MOL 学术arXiv.cs.AI › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
The FaCells. An Exploratory Study about LSTM Layers on Face Sketches Classifiers
arXiv - CS - Artificial Intelligence Pub Date : 2021-02-22 , DOI: arxiv-2102.11361
Xavier Ignacio González

Lines are human mental abstractions. A bunch of lines may form a drawing. A set of drawings can feed an LSTM network input layer, considering each draw as a list of lines and a line a list of points. This paper proposes the pointless motive to classify the gender of celebrities' portraits as an excuse for exploration in a broad, more artistic sense. Investigation results drove compelling ideas here discussed. The experiments compared different ways to represent draws to be input in a network and showed that an absolute format of coordinates (x, y) was a better performer than a relative one (Dx, Dy) with respect to prior points, most frequent in the reviewed literature. Experiments also showed that, due to the recurrent nature of LSTMs, the order of lines forming a drawing is a relevant factor for input in an LSTM classifier not studied before. A minimum 'pencil' traveled length criteria for line ordering proved suitable, possible by reducing it to a TSP particular instance. The best configuration for gender classification appears with an LSTM layer that returns the hidden state value for each input point step, followed by a global average layer along the sequence, before the output dense layer. That result guided the idea of removing the average in the network pipeline and return a per-point attribute score just by adjusting tensors dimensions. With this trick, the model detects an attribute in a drawing and also recognizes the points linked to it. Moreover, by overlapping filtered lines of portraits, an attribute's visual essence is depicted. Meet the FaCells.

中文翻译:

FaCells。人脸草图分类器上LSTM层的探索性研究

线条是人类的精神抽象。一束线可能会形成图形。一组工程图可以馈入LSTM网络输入层,将每个工程图视为线的列表,而将线视为点的列表。本文提出了一种毫无意义的动机,将名人肖像的性别分类为从更广泛,更具艺术意义上进行探索的借口。调查结果驱使人们在此讨论令人信服的想法。实验比较了表示网络中要输入的图形的不同方式,结果表明,相对于先前的点,坐标的绝对格式(x,y)相对于相对坐标(Dx,Dy)的性能更好,这在坐标系中最常见。评论文献。实验还表明,由于LSTM的重复性,构成图形的线的顺序是在以前未研究过的LSTM分类器中输入的相关因素。对于行排序的最小“铅笔”行进长度标准被证明是合适的,可以通过将其减少到TSP特定实例来实现。性别分类的最佳配置出现在LSTM层上,该层返回每个输入点步骤的隐藏状态值,然后是沿着序列的全局平均层,然后是输出密集层。该结果指导了删除网络管道中的平均值并仅通过调整张量尺寸来返回每点属性得分的想法。使用此技巧,模型可以检测图形中的属性,还可以识别与其链接的点。此外,通过重叠过滤的肖像线,可以描绘属性的视觉本质。认识FaCell。通过将其简化为TSP特定实例来实现。性别分类的最佳配置出现在LSTM层上,该层返回每个输入点步骤的隐藏状态值,然后是沿着序列的全局平均层,然后是输出密集层。该结果指导了删除网络管道中的平均值并仅通过调整张量尺寸来返回每点属性得分的想法。使用此技巧,模型可以检测图形中的属性,还可以识别与其链接的点。此外,通过重叠过滤的肖像线,可以描绘属性的视觉本质。认识FaCell。通过将其简化为TSP特定实例来实现。性别分类的最佳配置出现在LSTM层上,该层返回每个输入点步骤的隐藏状态值,然后是沿着序列的全局平均层,然后是输出密集层。该结果指导了删除网络管道中的平均值并仅通过调整张量尺寸来返回每点属性得分的想法。使用此技巧,模型可以检测图形中的属性,还可以识别与其链接的点。此外,通过重叠过滤的肖像线,可以描绘属性的视觉本质。认识FaCell。然后是沿着序列的全局平均层,在输出密集层之前。该结果指导了删除网络管道中的平均值并仅通过调整张量尺寸来返回每点属性得分的想法。使用此技巧,模型可以检测图形中的属性,还可以识别与其链接的点。此外,通过重叠过滤的肖像线,可以描绘属性的视觉本质。认识FaCell。然后是沿着序列的全局平均层,在输出密集层之前。该结果指导了删除网络管道中的平均值并仅通过调整张量尺寸来返回每点属性得分的想法。使用此技巧,模型可以检测图形中的属性,还可以识别与其链接的点。此外,通过重叠过滤的肖像线,可以描绘属性的视觉本质。认识FaCell。描绘了视觉本质。认识FaCell。描绘了视觉本质。认识FaCell。
更新日期:2021-02-24
down
wechat
bug