본문 바로가기

쓰기

 
저자 김누리*, 이진섭*, 이지형 (*: equal contribution) 
학회명 IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024 
학회명 (약자) CVPR 2024 
pp.  
학회시작일 2024-06-17 
학회종료일 2024-06-19 
비고  

Title : Learning with Structural Labels for Learning with Noisy Labels

Abstract : Deep Neural Networks (DNNs) have demonstrated remarkable performance across diverse domains and tasks with large-scale datasets. To reduce labeling costs, semi-automated and crowdsourcing labeling methods are developed, but their labels are inevitably noisy. Learning with Noisy Labels (LNL) approaches aim to train DNNs despite the presence of noisy labels. These approaches leverage the memorization effect to acquire more accurate labels through a process of relabeling and selection, subsequently using these refined labels for next training. However, these methods encounter a significant decrease in the model's generalization performance due to the inevitably existing noise labels. To overcome this limitation, we propose a new approach to enhance learning with noisy labels by incorporating additional distribution information—structural labels. In order to leverage additional distribution information for generalization, we utilize a reverse k-NN, which helps the model achieve a simpler feature manifold and avoid overfitting to noisy labels. The proposed method shows outperformed performance in multiple benchmark datasets with synthetic and real-world datasets.

    2024

      Learning with Structural Labels for Learning with Noisy Labels
      2024.02.27
      저자: 김누리*, 이진섭*, 이지형 (*: equal contribution)     학회명: IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024     학회명 (약자): CVPR 2024     학회시작일: 2024-06-17     학회종료일: 2024-06-19    
      STAGE: Simple Text Data Augmentation by Graph Exploration
      2024.02.28
      저자: 김호승, 강용훈, 이지형     학회명: The 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation     학회명 (약자): LREC-COLING 2024     학회시작일: 2024-05-20     학회종료일: 2024-05-25    
      TF-EDA: Efficient and Effective Text Data Augmentation
      2024.02.29
      저자: 김호승, 이지형, 김한별     학회명: The 24th International Symposium on Advanced Intelligent Systems     학회명 (약자): ISIS 2023     학회시작일: 2023-12-06     학회종료일: 2023-12-09    

    2023

    2022

      Reducing computational cost in federated ensemble learning via rank-one matrix
      2022.12.05
      저자: YongHoon Kang, HoSeung Kim, Jee-Hyong Lee     학회명: Joint 12th International Conference on Soft Computing and Intelligent Systems and 23rd International Symposium on Advanced Intelligent Systems     학회명 (약자): SCIS-ISIS 2022     학회시작일: 2022-11-29     학회종료일: 2022-12-02    

    2021