Papers

Learn about some of the frontline research that Saige researchers are engaged in together with our collaborators. While not all of this work may find their way into our products (if ever), it keeps us engaged in the latest trends and topics, and most of all, it’s fun!

    • Efficient neural network compression via transfer learning for machine vision inspection
    • Neurocomputing
      Seunghyeon Kim, Yung-Kyun Noh, Frank C.Park
      See More(Link)

      [ Abstract ]

      Several practical difficulties arise when trying to apply deep learning to image-based industrial inspection tasks: training datasets are difficult to obtain, each image must be inspected in milliseconds, and defects must be detected with 99% or greater accuracy. In this paper we show how, for image-based industrial inspection tasks, transfer learning can be leveraged to address these challenges. Whereas transfer learning is known to work well only when the source and target domain images are similar, we show that using ImageNet—whose images differ significantly from our target industrial domain—as the source domain, and performing transfer learning, works remarkably well. For one benchmark problem involving 5,520 training images, the resulting transfer-learned network achieves 99.90% accuracy, compared to only a 70.87% accuracy achieved by the same network trained from scratch. Further analysis reveals that the transfer-learned network produces a considerably more sparse and disentangled representation compared to the trained-from-scratch network. The sparsity can be exploited to compress the transfer-learned network up to 1/128 the original number of convolution filters with only a 0.48% drop in accuracy, compared to a drop of nearly 5% when compressing a trained-from-scratch network. Our findings are validated by extensive systematic experiments and empirical analysis.

    • A Riemannian geometric framework for manifold learning of non-Euclidean data
    • Advances in Data Analysis and Classification, 2020 (DOI 10.1007)
      Cheongjae Jang, Yung-Kyun Noh, and Frank Chongwoo Park
      See More(Link)

      [ Abstract ]

      A growing number of problems in data analysis and classification involve data that are non-Euclidean. For such problems, a naive application of vector space analysis algorithms will produce results that depend on the choice of local coordinates used to parametrize the data. At the same time, many data analysis and classification problems eventually reduce to an optimization, in which the criteria being minimized can be interpreted as the distortion associated with a mapping between two curved spaces. Exploiting this distortion minimizing perspective, we first show that manifold learning problems involving non-Euclidean data can be naturally framed as seeking a mapping between two Riemannian manifolds that is closest to being an isometry. A family of coordinate-invariant first-order distortion measures is then proposed that measure the proximity of the mapping to an isometry, and applied to manifold learning for non-Euclidean data sets. Case studies ranging from synthetic data to human mass-shape data demonstrate the many performance advantages of our Riemannian distortion minimization framework.

    • Autoencoding Under Normalization Constraints
    • ICML 2021
      Sangwoong Yoon, Yung-Kyun Noh, Frank Chongwoo Park
      See More(Link)

      [ Abstract ]

      Likelihood is a standard estimate for outlier detection. The specific role of the normalization constraint is to ensure that the out-of-distribution (OOD) regime has a small likelihood when samples are learned using maximum likelihood. Because autoencoders do not possess such a process of normalization, they often fail to recognize outliers even when they are obviously OOD. We propose the Normalized Autoencoder (NAE), a normalized probabilistic model constructed from an autoencoder. The probability density of NAE is defined using the reconstruction error of an autoencoder, which is differently defined in the conventional energy-based model. In our model, normalization is enforced by suppressing the reconstruction of negative samples, significantly improving the outlier detection performance. Our experimental results confirm the efficacy of NAE, both in detecting outliers and in generating in-distribution samples.

    • Age-group determination of living individuals using first molar images based on artificial intelligence
    • Scientific Reports
      Seunghyeon Kim, Yeon-Hee Lee, Yung-Kyun Noh, Frank C.Park, Q.-Schick Auh
      See More(Link)

      [ Abstract ]

      Dental age estimation of living individuals is difficult and challenging, and there is no consensus method in adults with permanent dentition. Thus, we aimed to provide an accurate and robust artificial intelligence (AI)-based diagnostic system for age-group estimation by incorporating a convolutional neural network (CNN) using dental X-ray image patches of the first molars extracted via panoramic radiography. The data set consisted of four first molar images from the right and left sides of the maxilla and mandible of each of 1586 individuals across all age groups, which were extracted from their panoramic radiographs. The accuracy of the tooth-wise estimation was 89.05 to 90.27%. Performance accuracy was evaluated mainly using a majority voting system and area under curve (AUC) scores. The AUC scores ranged from 0.94 to 0.98 for all age groups, which indicates outstanding capacity. The learned features of CNNs were visualized as a heatmap, and revealed that CNNs focus on differentiated anatomical parameters, including tooth pulp, alveolar bone level, or interdental space, depending on the age and location of the tooth. With this, we provided a deeper understanding of the most informative regions distinguished by age groups. The prediction accuracy and heat map analyses support that this AI-based age-group determination model is plausible and useful.