11/14 Applications of Graph Convolutional Networks (GCN) (김태균 교수/KAIST 전산학부)

작성자
kaistsoftware
작성일
2022-11-09 17:34
조회
2936
  • 강사 : 김태균 교수 (KAIST 전산학부)
  • 일시 : 2022. 11. 14 (월) 16:00~17:30
Graph convolution networks have been a vital tool for a variety of tasks in computer vision. Beyond predefined array data, graph representation with vertexes and edges capture inherent data structure better. 3D shapes in mesh are probably the best example in graphs, and a set of multi-dimensional data vectors and their relations are often cast as nodes and edges in a graph. I will present two example studies of our own on GCN, published at CVPR2021. In the first work, we focus on deep 3D morphable models that directly apply deep learning on 3D mesh data with a hierarchical structure to capture information at multiple scales. While great efforts have been made to design the convolution operator, how to best aggregate vertex features across hierarchical levels deserves further attention. In contrast to resorting to mesh decimation, we propose an attention based module to learn mapping matrices for better feature aggregation across hierarchical levels. Our proposed module for both mesh downsampling and upsampling achieves state-of-the art results on a variety of 3D shape datasets. In the second work, we propose a novel pool-based Active Learning framework constructed on a sequential Graph Convolution Network (GCN). Each images feature from a pool of data represents a node in the graph and the edges encode their similarities. With a small number of randomly sampled images as seed labelled examples, we learn the parameters of the graph to distinguish labelled vs unlabelled nodes. To this end, we utilise the graph node embeddings and their confidence scores and adapt sampling techniques such as CoreSet and uncertainty-based methods to query the nodes. Our method outperforms several competitive AL baselines such as VAAL, Learning Loss, CoreSet and attains the new state of-the-art performance on multiple applications.

* 강연자료
전체 119
번호 제목 작성자 작성일 추천 조회
공지사항
2024년 봄학기 콜로퀴엄 일정 안내
kaistsoftware | 2024.02.21 | 추천 1 | 조회 2270
kaistsoftware 2024.02.21 1 2270
118
4/2 LLM 기반 소프트웨어 공학의 현재와 전망 (유신 교수/KAIST 전산학부)
kaistsoftware | 2024.03.25 | 추천 0 | 조회 53
kaistsoftware 2024.03.25 0 53
117
3/26 하드웨어도 소프트웨어처럼 짜야한다 (강지훈 교수/KAIST 전산학부)
kaistsoftware | 2024.03.21 | 추천 0 | 조회 78
kaistsoftware 2024.03.21 0 78
116
3/19 자율주행과 안전 (배홍상 교수/KAIST 전산학부)
kaistsoftware | 2024.03.11 | 추천 0 | 조회 174
kaistsoftware 2024.03.11 0 174
115
3/12 에너지 효율적인 인공지능 학습 시스템 (권영진 교수/KAIST 전산학부)
kaistsoftware | 2024.03.05 | 추천 0 | 조회 231
kaistsoftware 2024.03.05 0 231
114
2/27 멀티-디바이스 모바일 플랫폼 (신인식 교수/KAIST 전산학부)
kaistsoftware | 2024.02.27 | 추천 0 | 조회 649
kaistsoftware 2024.02.27 0 649
113
11/20 Where is Autonomous Driving going? Boss, Traffic Jam Pilot, and the Future (배홍상 교수/KAIST 전산학부, Zeta Mobility)
kaistsoftware | 2023.11.16 | 추천 1 | 조회 2052
kaistsoftware 2023.11.16 1 2052
112
11/14 데이터 품질 문제에 견고한 AI 기술 (이재길 교수/KAIST 전산학부)
kaistsoftware | 2023.11.16 | 추천 1 | 조회 1442
kaistsoftware 2023.11.16 1 1442
111
11/6 인터랙션 중심 AI (김주호 교수/KAIST 전산학부)
kaistsoftware | 2023.11.01 | 추천 0 | 조회 1579
kaistsoftware 2023.11.01 0 1579
110
10/30 사모펀드의 이해 - 펀드구성과 투자구조를 중심으로 (최원호 교수/KAIST 전산학부)
kaistsoftware | 2023.10.26 | 추천 0 | 조회 1576
kaistsoftware 2023.10.26 0 1576
109
10/23 Robotic Companion: natural language to dexterous manipulation (박대형 교수/KAIST 전산학부)
kaistsoftware | 2023.10.20 | 추천 0 | 조회 1525
kaistsoftware 2023.10.20 0 1525