• ETRI Journal
• /
• v.41 no.2
• /
• pp.242-253
• /
• 2019

We devise a layer-wise hint training method to improve the existing hint-based knowledge distillation (KD) training approach, which is employed for knowledge transfer in a teacher-student framework using a residual network (ResNet). To achieve this objective, the proposed method first iteratively trains the student ResNet and incrementally employs hint-based information extracted from the pretrained teacher ResNet containing several hint and guided layers. Next, typical softening factor-based KD training is performed using the previously estimated hint-based information. We compare the recognition accuracy of the proposed approach with that of KD training without hints, hint-based KD training, and ResNet-based layer-wise pretraining using reliable datasets, including CIFAR-10, CIFAR-100, and MNIST. When using the selected multiple hint-based information items and their layer-wise transfer in the proposed method, the trained student ResNet more accurately reflects the pretrained teacher ResNet's rich information than the baseline training methods, for all the benchmark datasets we consider in this study.

• Korean Journal of Computational Design and Engineering
• /
• v.10 no.6
• /
• pp.392-401
• /
• 2005

2D CAD is being replaced by 3D CAD to improve efficiency of product design and manufacturing. Therefore, converting legacy 2D drawings into 3D solid models is required. CSG based approaches construct solid models from orthographic views more efficiently than traditional B-rep based approaches. A major limitation of CSG based approaches has been the limited domain of objects that can be handled. This paper aims at extending the capabilities of CSG based approaches by proposing hint-based recognition of interacting solids of revolution which can handle interacting solids of revolution as well as isolated solids of revolution.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.5
• /
• pp.35-41
• /
• 2017

In this paper, we analyze the performance of the recently introduced Hint-knowledge distillation (KD) training approach based on the teacher-student framework for knowledge distillation and knowledge transfer. As a deep neural network (DNN) considered in this paper, the deep residual network (ResNet), which is currently regarded as the latest DNN, is used for the teacher-student framework. Therefore, when implementing the Hint-KD training, we investigate the impact on the weight of KD information based on the soften factor in terms of classification accuracy using the widely used open deep learning frameworks, Caffe. As a results, it can be seen that the recognition accuracy of the student model is improved when the fixed value of the KD information is maintained rather than the gradual decrease of the KD information during training.

• Korean Journal of Computational Design and Engineering
• /
• v.3 no.1
• /
• pp.68-85
• /
• 1998

Solid modeling refers to techniques for unambiguous representations of three-dimensional objects. Feature recognition is a sub-discipline focusing on the design and implementation of algorithms for detecting manufacturing information such as holes, slots, etc. in a solid model. Automated feature recognition has been an active research area in stolid modeling for many years, and is considered to be a critical component for CAD/CAM integration. This paper gives a technical overview of the state of the art in feature recognition research. Rather than giving an exhaustive survey, I focus on the three currently dominant feature recognition technologies: graph-based algorithms, volumetric decomposition techniques, and hint-based geometric reasoning. For each approach, I present a detailed description of the algorithms being employed along with some assessments of the technology. I conclude by outlining important open research and development issues.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.1
• /
• pp.108-113
• /
• 2022

Speech recognition in noise situation is an important skill for effective communication. Hearing In Noise Test (HINT) has been suggested as a clinical tool to evaluate these aspects. However, this tool has not been used widely in domestic clinics. In this study, psychophysical aspects of HINT and burdens in clinical application were analyzed to improve the applicability of the tool. The difficulty in understanding speech in the elderly population is due to hearing loss based on aging of peripheral and central auditory pathways. As typical clinical cases, HINT scores for young and elderly listeners (20s vs 70s) were compared. Four conditions of HINT test were Quiet (Q), Noise Front (NF), Noise Right (NR), and Noise Left (NL). Quantitative scores showed that the elderly listener required more Signal to Noris Ratio (SNR) values than the younger counterpart in noisy situations. Although both showed Binaural Masking Level Difference (BMLD) effect, the strength was smaller in the elder. However, the age-matched normalized data were not established in detail for clinical application. Confirmed usefulness of HINT and the related improvement in clinical measuring procedure were suggested.

• The KIPS Transactions:PartC
• /
• v.17C no.1
• /
• pp.27-36
• /
• 2010

In Web registration pages and online polling applications, CAPTCHA(Completely Automated Public Turing Test To Tell Computers and Human Apart) is used for distinguishing human users from automated programs. Text-based CAPTCHAs have been widely used in many popular Web sites in which distorted text is used. However, because the advanced optical character recognition techniques can recognize the distorted texts, the reliability becomes low. Image-based CAPTCHAs have been proposed to improve the reliability of the text-based CAPTCHAs. However, these systems also are known as having some drawbacks. First, some image-based CAPTCHA systems with small number of image files in their image dictionary is not so reliable since attacker can recognize images by repeated executions of machine learning programs. Second, users may feel uncomfortable since they have to try CAPTCHA tests repeatedly when they fail to input a correct keyword. Third, some image-base CAPTCHAs require high communication cost since they should send several image files for one CAPTCHA. To solve these problems of image-based CAPTCHA, this paper proposes a new CAPTCHA based on both image and text. In this system, an image and keywords are integrated into one CAPTCHA image to give user a hint for the answer keyword. The proposed CAPTCHA can help users to input easily the answer keyword with the hint in the fused image. Also, the proposed system can reduce the communication costs since it uses only a fused image file for one CAPTCHA. To improve the reliability of the image-text fusion CAPTCHA, we also propose a dynamic building method of large image dictionary from gathering huge amount of images from theinternet with filtering phase for preserving the correctness of CAPTCHA images. In this paper, we proved that the proposed image-text fusion CAPTCHA provides users more convenience and high reliability than the image-based CAPTCHA through experiments.