Skip to Main Content

An official website of the United States government

About this Publication
Multi-path x-D Recurrent Neural Networks for Collaborative Image Classification.
Pubmed ID
32863584 (View this publication on the PubMed website)
Digital Object Identifier
Neurocomputing. 2020 Jul 15; Volume 397: Pages 48-59
Gao R, Huo Y, Bao S, Tang Y, Antic SL, Epstein ES, Deppen S, Paulson AB, Sandler KL, Massion PP, Landman BA
  • Electrical Engineering and Computer Science, Vanderbilt University, Nashville, TN, USA 37235, Vanderbilt University Medical Center, Nashville, TN, USA 37235.

With the rapid development of image acquisition and storage, multiple images per class are commonly available for computer vision tasks (e.g., face recognition, object detection, medical imaging, etc.). Recently, the recurrent neural network (RNN) has been widely integrated with convolutional neural networks (CNN) to perform image classification on ordered (sequential) data. In this paper, by permutating multiple images as multiple dummy orders, we generalize the ordered "RNN+CNN" design (longitudinal) to a novel unordered fashion, called Multi-path x-D Recurrent Neural Network (MxDRNN) for image classification. To the best of our knowledge, few (if any) existing studies have deployed the RNN framework to unordered intra-class images to leverage classification performance. Specifically, multiple learning paths are introduced in the MxDRNN to extract discriminative features by permutating input dummy orders. Eight datasets from five different fields (MNIST, 3D-MNIST, CIFAR, VGGFace2, and lung screening computed tomography) are included to evaluate the performance of our method. The proposed MxDRNN improves the baseline performance by a large margin across the different application fields (e.g., accuracy from 46.40% to 76.54% in VGGFace2 test pose set, AUC from 0.7418 to 0.8162 in NLST lung dataset). Additionally, empirical experiments show the MxDRNN is more robust to category-irrelevant attributes (e.g., expression, pose in face images), which may introduce difficulties for image classification and algorithm generalizability. The code is publicly available.

Related CDAS Studies
Related CDAS Projects