• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.8
• /
• pp.2895-2912
• /
• 2014

Content-based image retrieval has been the most important technique for managing huge amount of images. The fundamental yet highly challenging problem in this field is how to measure the content-level similarity based on the low-level image features. The primary difficulties lie in the great variance within images, e.g. background, illumination, viewpoint and pose. Intuitively, an ideal similarity measure should be able to adapt the data distribution, discover and highlight the content-level information, and be robust to those variances. Motivated by these observations, we in this paper propose a probabilistic similarity learning approach. We first model the distribution of low-level image features and derive the free energy kernel (FEK), i.e., similarity measure, based on the distribution. Then, we propose a learning approach for the derived kernel, under the criterion that the kernel outputs high similarity for those images sharing the same class labels and output low similarity for those without the same label. The advantages of the proposed approach, in comparison with previous approaches, are threefold. (1) With the ability inherited from probabilistic models, the similarity measure can well adapt to data distribution. (2) Benefitting from the content-level hidden variables within the probabilistic models, the similarity measure is able to capture content-level cues. (3) It fully exploits class label in the supervised learning procedure. The proposed approach is extensively evaluated on two well-known databases. It achieves highly competitive performance on most experiments, which validates its advantages.

• Journal of the Korean Society for information Management
• /
• v.25 no.3
• /
• pp.27-39
• /
• 2008

In bibliographic data, the use of personal names to indicate authors makes it difficult to specify a particular author since there are numerous authors whose personal names are the same. Resolving same-name author instances into different individuals is called author resolution, which consists of two steps: calculating author similarities and then clustering same-name author instances into different person groups. Author similarities are computed from similarities of author-related bibliographic features such as coauthors, titles of papers, publication information, using supervised or unsupervised methods. Supervised approaches employ machine learning techniques to automatically learn the author similarity function from author-resolved training samples. So far however, a few machine learning methods have been investigated for author resolution. This paper provides a comparative evaluation of a variety of recent high-performing machine learning techniques on author disambiguation, and compares several methods of processing author disambiguation features such as coauthors and titles of papers.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.19-28
• /
• 2022

In this paper, we propose the Detector Scheduler which determines the best tracking-by-detection (TBD) mechanism to perform real-time high-accurate multi-object tracking (MOT). The Detector Scheduler determines whether to run a detector by measuring the dissimilarity of features between different frames. Furthermore, we propose a self-supervision method to learn the Detector Scheduler with tracking results since it is difficult to generate ground truth (GT) for learning the Detector Scheduler. Our proposed self-supervision method generates pseudo labels on whether to run a detector when the dissimilarity of the object cardinality or appearance between frames increases. To this end, we propose the Detector Scheduling Loss to learn the Detector Scheduler. As a result, our proposed method achieves real-time high-accurate multi-object tracking by boosting the overall tracking speed while keeping the tracking accuracy at most.

• Genomics & Informatics
• /
• v.18 no.1
• /
• pp.2.1-2.11
• /
• 2020

In this paper, we propose a new approach to detecting outliers in a set of segmented genomes of the flu virus, a data set with a heterogeneous set of sequences. The approach has the following computational phases: feature extraction, which is a mapping into feature space, alignment-free distance measure to measure the distance between any two segmented genomes, and a mapping into distance space to analyze a quantum of distance values. The approach is implemented using supervised and unsupervised learning modes. The experiments show robustness in detecting outliers of the segmented genome of the flu virus.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.482-482
• /
• 2000

The essential requirements of neural network for human skill transfer are fast convergence, high storage capacity, and strong noise immunity. Bidirectional associative memory(BAM) suffering from low storage capacity and abundance of spurious memories is rarely used for skill transfer application though it has fast and wide association characteristics for visual data. This paper suggests generalization of classical BAM structure and new learning algorithm which uses supervised learning to guarantee perfect recall starting with correlation matrix. The generalization is validated to accelerate convergence speed, to increase storage capacity, to lessen spurious memories, to enhance noise immunity, and to enable multiple association using simulation work.

• Broadcasting and Media Magazine
• /
• v.27 no.2
• /
• pp.19-25
• /
• 2022

본 고에서는 최근 컴퓨터 비전 분야에서 가장 활발히 연구되고 있는 분야 중에 하나인 자가 학습(Self-supervised Learning) 기술의 동향과 향후 방향성에 대해서 논의한다. 컴퓨터 비전 분야에서의 자가 학습 기술은 최근에 Contrastive Learning 기법을 활용하여 활발하게 연구되고 있는데, 이를 위한 좋은 Positive와 Negative를 어떻게 추출할까에 대한 고민으로 수많은 연구들이 진행되어 왔다. 본 고에서는 이러한 방향성에서 대표적인 몇 가지의 방법론에 대해서 논의하고 이의 한계점을 언급하며 컴퓨터 비전 분야에서 자가 학습 기법이 가야 할 방향성에 대해서 논의하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.347-350
• /
• 2021

본 논문에서는 지도학습(Supervised Learning)알고리즘을 사용하는 모듈러 스파이킹 신경회로망(Modular Spiking Neural Networks)에서 학습의 진행 상황에 맞추어 학습용 데이터를 사용하는 다중 단계 학습알고리즘을 제안한다. 또한 컴퓨터 시뮬레이션에 의하여 항공영상 클러스터링 문제에 적용한 결과를 보임으로써 실제적인 문제에서의 적용 타당성과 가능성을 보인다.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.139-147
• /
• 2021

This paper introduces and implements a Sound Event Detection (SED) system based on weakly-supervised learning where only part of the data is labeled, and analyzes the effect of parameters. The SED system estimates the classes and onset/offset times of events in the acoustic signal. In order to train the model, all information on the event class and onset/offset times must be provided. Unfortunately, the onset/offset times are hard to be labeled exactly. Therefore, in the weakly-supervised task, the SED model is trained by "strongly labeled data" including the event class and activations, "weakly labeled data" including the event class, and "unlabeled data" without any label. Recently, the SED systems using the mean-teacher model are widely used for the task with several parameters. These parameters should be chosen carefully because they may affect the performance. In this paper, performance analysis was performed on parameters, such as the feature, moving average parameter, weight of the consistency cost function, ramp-up length, and maximum learning rate, using the data of DCASE 2020 Task 4. Effects and the optimal values of the parameters were discussed.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.185-207
• /
• 2022

Recently, with the development of deep learning technology, researches to apply a deep learning algorithm to analyze unstructured data such as text and images are being actively conducted. Text classification has been studied for a long time in academia and industry, and various attempts are being performed to utilize data characteristics to improve classification performance. In particular, a hierarchical relationship of labels has been utilized for hierarchical classification. However, the top-down approach mainly used for hierarchical classification has a limitation that misclassification at a higher level blocks the opportunity for correct classification at a lower level. Therefore, in this study, we propose a methodology for classifying hierarchical data using the autoencoder-based deeply supervised network that high-level classification does not block the low-level classification while considering the hierarchical relationship of labels. The proposed methodology adds a main classifier that predicts a low-level label to the autoencoder's latent variable and an auxiliary classifier that predicts a high-level label to the hidden layer of the autoencoder. As a result of experiments on 22,512 academic papers to evaluate the performance of the proposed methodology, it was confirmed that the proposed model showed superior classification accuracy and F1-score compared to the traditional supervised autoencoder and DNN model.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.