• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.540-542
• /
• 2023

Due to the serious issues posed by facial manipulation technologies, many researchers are becoming increasingly interested in the identification of face forgeries. The majority of existing face forgery detection methods leverage powerful data adaptation ability of neural network to derive distinguishing traits. These deep learning-based detection methods frequently treat the detection of fake faces as a binary classification problem and employ softmax loss to track CNN network training. However, acquired traits observed by softmax loss are insufficient for discriminating. To get over these limitations, in this study, we introduce a novel discriminative feature learning based on Vision Transformer architecture. Additionally, a separation-center loss is created to simply compress intra-class variation of original faces while enhancing inter-class differences in the embedding space.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.347-348
• /
• 2024

본 논문에서는 철도 구성요소 모니터링을 위한 효율적인 객체 분할 기법으로 사전학습된 SegFormer 모델의 적용을 제안하고, 객체 분할을 위해 보편적으로 사용되는 U-Net 모델과의 성능 비교 분석을 진행하였다. 철도의 주요 구성요소인 선로, 침목, 고정 장치, 배경을 분할할 수 있도록 라벨링된 데이터셋을 학습에 사용하였다. SegFormer 모델이 대조군인 U-Net보다 성능이 Jaccard Score 기준 5.29% 향상됨에 따라 Vision Transformer 기반의 모델이 기존 CNN 기반 모델의 이미지의 전역적인 문맥을 파악하기 상대적으로 어렵다는 한계를 극복하고, 철도 구성요소 객체 분할에 더욱 효율적인 모델임을 확인한다.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.795-800
• /
• 2016

In image classification, recent CNNs compete with human performance. However, there are limitations in more general recognition. Herein we deal with indoor images that contain too much information to be directly processed and require information reduction before recognition. To reduce the amount of data processing, typically variational inference or variational Bayesian methods are suggested for object detection. However, these methods suffer from the difficulty of marginalizing over the given space. In this study, we propose an image-text integrated recognition system using active vision based on Spatial Transformer Networks. The system attempts to efficiently sample a partial region of a given image for a given language information. Our experimental results demonstrate a significant improvement over traditional approaches. We also discuss the results of qualitative analysis of sampled images, model characteristics, and its limitations.

• Journal of the Korea Computer Graphics Society
• /
• v.30 no.3
• /
• pp.109-123
• /
• 2024

Research into vision-based end-to-end autonomous driving systems utilizing deep learning and reinforcement learning has been steadily increasing. These systems typically encode continuous and high-dimensional vehicle states, such as location, velocity, orientation, and sensor data, into latent features, which are then decoded into a vehicular control policy. The complexity of urban driving environments necessitates the use of state representation learning through networks like Variational Autoencoders (VAEs) or Convolutional Neural Networks (CNNs). This paper analyzes the impact of different image state encoding methods on reinforcement learning performance in autonomous driving. Experiments were conducted in the CARLA simulator using RGB images and semantically segmented images captured by the vehicle's front camera. These images were encoded using VAE and Vision Transformer (ViT) networks. The study examines how these networks influence the agents' learning outcomes and experimentally demonstrates the role of each state representation technique in enhancing the learning efficiency and decision- making capabilities of autonomous driving systems.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.3
• /
• pp.140-147
• /
• 2024

In the Republic of Korea, people with hearing impairments are the second-largest demographic within the registered disability community, following those with physical disabilities. Despite this demographic significance, research on sign language translation technology is limited due to several reasons including the limited market size and the lack of adequately annotated datasets. Despite the difficulties, a few researchers continue to improve the performacne of sign language translation technologies by employing the recent advance of deep learning, for example, the transformer architecture, as the transformer-based models have demonstrated noteworthy performance in tasks such as action recognition and video classification. This study focuses on enhancing the recognition performance of sign language translation by combining transformers with 3D-CNN. Through experimental evaluations using the PHOENIX-Wether-2014T dataset [1], we show that the proposed model exhibits comparable performance to existing models in terms of Floating Point Operations Per Second (FLOPs).

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.749-752
• /
• 2021

오늘날 인공지능(Artificial Intelligence, AI) 분야에서 가장 구현하기 어려운 분야 중 하나는 추론이다. 근래 추론 분야에서 영상과 언어가 결합한 다중 모드(Multi-modal) 환경에서 영상 기반의 질의 응답(Visual Question Answering, VQA) 과업에 대한 AI 모델이 발표됐다. 얼마 지나지 않아 VQA 모델의 성능을 개선한 GVQA(Grounded Visual Question Answering) 모델도 발표됐다. 하지만 아직 GVQA 모델도 완벽한 성능을 내진 못한다. 본 논문에서는 GVQA 모델의 성능 개선을 위해 VCC(Visual Concept Classifier) 모델을 ViT-G(Vision Transformer-Giant)/14로 변경하고, ACP(Answer Cluster Predictor) 모델을 GPT(Generative Pretrained Transformer)-3으로 변경한다. 이와 같은 방법들은 성능을 개선하는 데 큰 도움이 될 수 있다고 사료된다.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.199-206
• /
• 2023

This study utilizes deep learning algorithms to automatically classify construction waste into three categories: wood waste, plastic waste, and concrete waste. Two models, VGG-16 and ViT (Vision Transformer), which are convolutional neural network image classification algorithms and NLP-based models that sequence images, respectively, were compared for their performance in classifying construction waste. Image data for construction waste was collected by crawling images from search engines worldwide, and 3,000 images, with 1,000 images for each category, were obtained by excluding images that were difficult to distinguish with the naked eye or that were duplicated and would interfere with the experiment. In addition, to improve the accuracy of the models, data augmentation was performed during training with a total of 30,000 images. Despite the unstructured nature of the collected image data, the experimental results showed that VGG-16 achieved an accuracy of 91.5%, and ViT achieved an accuracy of 92.7%. This seems to suggest the possibility of practical application in actual construction waste data management work. If object detection techniques or semantic segmentation techniques are utilized based on this study, more precise classification will be possible even within a single image, resulting in more accurate waste classification

• Smart Structures and Systems
• /
• v.32 no.1
• /
• pp.23-35
• /
• 2023

Steel bolted joint is an important part of steel structure, and its damage directly affects the bearing capacity and durability of steel structure. Currently, the existing research mainly focuses on the identification of corroded bolts and corroded bolts respectively, and there are few studies on multiple states. A detection framework of corroded and loosened bolts is proposed in this study, and the innovations can be summarized as follows: (i) Vision Transformer (ViT) is introduced to replace the third and fourth C3 module of you-only-look-once version 5s (YOLOv5s) algorithm, which increases the attention weights of feature channels and the feature extraction capability. (ii) Three states of the steel bolts are considered, including corroded bolt, bolt missing and clean bolt. (iii) Line segment detector (LSD) is introduced for bolt rotation angle calculation, which realizes bolt looseness detection. The improved YOLOv5s model was validated on the dataset, and the mean average precision (mAP) was increased from 0.902 to 0.952. In terms of a lab-scale joint, the performance of the LSD algorithm and the Hough transform was compared from different perspective angles. The error value of bolt loosening angle of the LSD algorithm is controlled within 1.09%, less than 8.91% of the Hough transform. Furthermore, the proposed framework was applied to fullscale joints of a steel bridge in China. Synthetic images of loosened bolts were successfully identified and the multiple states were well detected. Therefore, the proposed framework can be alternative of monitoring steel bolted joints for management department.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.31-39
• /
• 2023

In this paper, we propose an Internal/External Knowledge Distillation (IEKD), which utilizes both external correlations between feature maps of heterogeneous models and internal correlations between feature maps of the same model for transferring knowledge from a teacher model to a student model. To achieve this, we transform feature maps into a sequence format and extract new feature maps suitable for knowledge distillation by considering internal and external correlations through a transformer. We can learn both internal and external correlations by distilling the extracted feature maps and improve the accuracy of the student model by utilizing the extracted feature maps with feature matching. To demonstrate the effectiveness of our proposed knowledge distillation method, we achieved 76.23% Top-1 image classification accuracy on the CIFAR-100 dataset with the "ResNet-32×4/VGG-8" teacher and student combination and outperformed the state-of-the-art KD methods.

• Journal of Platform Technology
• /
• v.11 no.6
• /
• pp.34-46
• /
• 2023

The design of non-pneumatic tires, which are created by filling the space between the wheel and the tread with elastomeric compounds or polygonal spokes, has become an important research topic in the automotive and aerospace industries. In this study, a system was designed for the design of non-pneumatic tires through the implementation of a generative adversarial network. We specifically examined factors that could impact the design, including the type of non-pneumatic tire, its intended usage environment, manufacturing techniques, distinctions from pneumatic tires, and how spoke design affects load distribution. Using OpenCV, various shapes and spoke configurations were generated as images, and a GAN model was trained on the projected GANs to generate shapes and spokes for non-pneumatic tire designs. The designed non-pneumatic tires were labeled as available or not, and a Vision Transformer image classification AI model was trained on these labels for classification purposes. Evaluation of the classification model show convergence to a near-zero loss and a 99% accuracy rate confirming the generation of non-pneumatic tire designs.