• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.630-632
• /
• 2023

어텐션 메커니즘은 딥 뉴럴네트워크에 결합하여 언어 생성 모델에서 성능을 개선하였고, 이러한 성공은 다양한 신호처리 분야에 응용 및 확장되고 있다. 특정 입력 신호 부분에 선택적으로 집중함으로써, 어텐션 모델은 음성 인식, 이미지와 비디오 처리, 그리고 생체인식 등의 분야에서 더 높은 성능을 보여주고 있다. 어텐션 기반 모델은 심전도 신호를 이용한 개인식별 및 부정맥검출, 뇌파도 신호를 이용한 발작유형분류 및 수면 단계 분류, 근전도 신호를 이용한 제스처 인식 등에 사용되고 있다. 어텐션 메커니즘은 딥 뉴럴네트워크의 해석 가능성과 설명 가능성을 향상시키기 위해 사용되기도 한다. 신호 처리 분야에서의 어텐션 모델 연구는 지속적으로 진행 중이며, 다른 분야에서의 잠재력 탐구에 대한 관심이 높아지고 있다. 따라서 본 논문은 어텐션 메카니즘을 이용한 생체신호처리 연구 동향 분석을 수행한다.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.25 no.4
• /
• pp.381-389
• /
• 2022

Detecting partially occluded objects is difficult due to the appearances and shapes of occluders are highly variable. These variabilities lead to challenges of localizing accurate bounding box or classifying objects with visible object parts. To address these problems, we propose a two-stage part-based attention approach for robust object detection under partial occlusion. First, our part attention network(PAN) captures the important object parts and then it is used to generate weighted object features. Based on the weighted features, the re-weighted object features are produced by our reinforced PAN(RPAN). Experiments are performed on our collected military vehicle dataset and synthetic occlusion dataset. Our method outperforms the baselines and demonstrates the robustness of detecting objects under partial occlusion.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.6
• /
• pp.235-242
• /
• 2021

In this work, we develop a Korean dependency parser based on a stack-pointer network that consists of a pointer network and an internal stack. The parser has an encoder and decoder and builds a dependency tree for an input sentence in a depth-first manner. The encoder of the parser encodes an input sentence, and the decoder selects a child for the word at the top of the stack at each step. Since the parser has the internal stack where a search path is stored, the parser can utilize information of previously derived subtrees when selecting a child node. Previous studies used only a grandparent and the most recently visited sibling without considering a subtree structure. In this paper, we introduce graph attention networks that can represent a previously derived subtree. Then we modify our parser based on the stack-pointer network to utilize subtree information produced by the graph attention networks. After training the dependency parser using Sejong and Everyone's corpus, we evaluate the parser's performance. Experimental results show that the proposed parser achieves better performance than the previous approaches at sentence-level accuracies when adopting 2-depth graph attention networks.

• Journal of Advanced Navigation Technology
• /
• v.27 no.2
• /
• pp.190-196
• /
• 2023

Recently, following the development of LIDAR technology which can detect distance from the object, the interest for LIDAR based 3D object detection network is getting higher. Previous networks generate inaccurate localization results due to spatial information loss during voxelization and downsampling. In this study, we propose an attention-based convergence method and a camera-LIDAR convergence system to acquire high-level features and high positional accuracy. First, by introducing the attention method into the Voxel-RCNN structure, which is a grid-based 3D object detection network, the multi-scale sparse 3D convolution feature is effectively fused to improve the performance of 3D object detection. Additionally, we propose the late-fusion mechanism for fusing outcomes in 3D object detection network and 2D object detection network to delete false positive. Comparative experiments with existing algorithms are performed using the KITTI data set, which is widely used in the field of autonomous driving. The proposed method showed performance improvement in both 2D object detection on BEV and 3D object detection. In particular, the precision was improved by about 0.54% for the car moderate class compared to Voxel-RCNN.