Evaluation of metric and representation learning approaches: Effects of representations driven by relative distance on the performance.
Evaluation of metric and representation learning approaches: Effects of representations driven by relative distance on the performance.
复制标题
度量和表示学习方法的评估：相对距离驱动的表示对性能的影响。
DOI：
10.1109/imsa58542.2023.10217475
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Girgis,HaniZ
中科院分区：
文献类型：
--
作者：
Garza,AnthonyB;Garcia,Rolando;Halfon,MarcS;Girgis,HaniZ
最近出现了几种用于度量学习的深度神经网络架构。我们问哪种架构在测量图像之间的相似性或不相似性方面是最有效的。为此，我们在标准图像集上评估了六个网络。我们评估了变分自编码器，暹罗网络，三重网络，以及与暹罗或三重网络相结合的变分自编码器。这些网络与由多个可分离卷积层组成的基线网络进行了比较。我们的研究揭示了以下内容：（i）由于学习相对距离而不是绝对距离，三元组架构被证明是最有效的架构;（ii）将自动编码器与学习度量的网络相结合（例如，Siamese或三重网络）是没有根据的;（iii）基于可分离卷积层的架构是三重网络的合理简单替代方案。这些结果可能会通过鼓励架构师开发利用可分离卷积和相对距离的高级网络来影响我们的领域。
Several deep neural network architectures have emerged recently for metric learning. We asked which architecture is the most effective in measuring the similarity or dissimilarity among images. To this end, we evaluated six networks on a standard image set. We evaluated variational autoencoders, Siamese networks, triplet networks, and variational auto-encoders combined with Siamese or triplet networks. These networks were compared to a baseline network consisting of multiple separable convolutional layers. Our study revealed the following: (i) the triplet architecture proved the most effective one due to learning a relative distance — not an absolute distance; (ii) combining auto-encoders with networks that learn metrics (e.g., Siamese or triplet networks) is unwarranted; and (iii) an architecture based on separable convolutional layers is a reasonable simple alternative to triplet networks. These results can potentially impact our field by encouraging architects to develop advanced networks that take advantage of separable convolution and relative distance.