DeepDiffusion: Unsupervised Learning of Retrieval-Adapted Representations via Diffusion-Based Ranking on Latent Feature Manifold-猫眼课题宝

DOI：

10.1109/access.2022.3218909

发表时间：

2021-12

期刊：

IEEE Access

影响因子：

3.9

通讯作者：

中科院分区：

计算机科学3区

文献类型：

作者：

T. Furuya;Ryutarou Ohbuchi

无监督的特征表示学习是一个具有挑战性但又重要的问题，用于分析大量没有语义标签的多媒体数据。最近提出的基于神经网络的无监督学习方法成功地获得了适合多媒体数据分类的功能。但是，对适合基于内容的匹配，比较或检索多媒体数据的特征表示形式的无监督学习尚未得到很好的探索。为了获得此类检索适应的功能，我们介绍了将扩散距离与基于神经网络的无监督特征学习相结合的想法。这个想法被认为是一种称为DeepDiffusion（DD）的新颖算法。 DD同时优化了两个组件，即深神经网络嵌入的特征，以及一个利用潜在特征歧管扩散的距离度量。 DD依赖其损失功能，但不依赖编码器体系结构。因此，它可以应用于及其各自的编码器体系结构的不同多媒体数据类型。使用3D形状和2D图像的实验评估证明了DD算法的多功能性以及高精度。代码可从https://github.com/takahikof/deepdiffusion获得

Unsupervised learning of feature representations is a challenging yet important problem for analyzing a large collection of multimedia data that do not have semantic labels. Recently proposed neural network-based unsupervised learning approaches have succeeded in obtaining features appropriate for classification of multimedia data. However, unsupervised learning of feature representations adapted to content-based matching, comparison, or retrieval of multimedia data has not been explored well. To obtain such retrieval-adapted features, we introduce the idea of combining diffusion distance on a feature manifold with neural network-based unsupervised feature learning. This idea is realized as a novel algorithm called DeepDiffusion (DD). DD simultaneously optimizes two components, a feature embedding by a deep neural network and a distance metric that leverages diffusion on a latent feature manifold, together. DD relies on its loss function but not encoder architecture. It can thus be applied to diverse multimedia data types with their respective encoder architectures. Experimental evaluation using 3D shapes and 2D images demonstrates versatility as well as high accuracy of the DD algorithm. Code is available at https://github.com/takahikof/DeepDiffusion

DeepDiffusion: Unsupervised Learning of Retrieval-Adapted Representations via Diffusion-Based Ranking on Latent Feature Manifold

文献摘要

相似文献