Contents

Improving unsupervised image clustering with robust learning

Park, Sungwon / Han, Sungwon / Kim, Sundong / Kim, Danu / Park, Sungkyu / Hong, Seunghoon / Cha, Meeyoung

  • 51 ITEM VIEW
  • 0 DOWNLOAD
Abstract

Unsupervised image clustering methods often introduce alternative objectives to indirectly train the model and are subject to faulty predictions and overconfident results. To overcome these challenges, the current research proposes an innovative model RUC that is inspired by robust learning. RUC’s novelty is at utilizing pseudo-labels of existing image clustering models as a noisy dataset that may include misclassified samples. Its retraining process can revise misaligned knowledge and alleviate the overconfidence problem in predictions. The model’s flexible structure makes it possible to be used as an add-on module to other clustering methods and helps them achieve better performance on multiple datasets. Extensive experiments show that the proposed model can adjust the model confidence with better calibration and gain additional robustness against adversarial noise.

Issue Date
2021-06-24
Publisher
IEEE Computer Society
URI
https://archives.kdischool.ac.kr/handle/11125/54876
10.1109/CVPR46437.2021.01210
URL
https://ieeexplore.ieee.org/document/9578903
Conf. Name
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Place
US
Conference Date
2021-06-19
ISSN
1063-6919
Files in This Item:
    There are no files associated with this item.

Click the button and follow the links to connect to the full text. (KDI CL members only)

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

상단으로 이동