Ajou University repository

Robust Asymmetric Loss for Multi-Label Long-Tailed Learningoa mark
Citations

SCOPUS

0

Citation Export

Publication Year
2023-01-01
Journal
Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023
Publisher
Institute of Electrical and Electronics Engineers Inc.
Citation
Proceedings - 2023 IEEE/CVF International Conference on Computer Vision Workshops, ICCVW 2023, pp.2703-2712
Keyword
Asymmetric LossLong tailed LearningMulti label Classification
Mesh Keyword
Asymmetric lossHyper-parameterLong tailed learningLoss functionsMedical dataMedical image classificationMulti-label classificationsMulti-labelsOverfittingTraining sample
All Science Classification Codes (ASJC)
Artificial IntelligenceComputer Science ApplicationsComputer Vision and Pattern Recognition
Abstract
In real medical data, training samples typically show long-tailed distributions with multiple labels. Class distribution of the medical data has a long-tailed shape, in which the incidence of different diseases is quite varied, and at the same time, it is not unusual for images taken from symptomatic patients to be multi-label diseases. Therefore, in this paper, we concurrently address these two issues by putting forth a robust asymmetric loss on the polynomial function. Since our loss tackles both long-tailed and multi-label classification problems simultaneously, it leads to a complex design of the loss function with a large number of hyper-parameters. Although a model can be highly fine-tuned due to a large number of hyper-parameters, it is difficult to optimize all hyper-parameters at the same time, and there might be a risk of overfitting a model. Therefore, we regularize the loss function using the Hill loss approach, which is beneficial to be less sensitive against the numerous hyper-parameters so that it reduces the risk of overfitting the model. For this reason, the proposed loss is a generic method that can be applied to most medical image classification tasks and does not make the training process more time-consuming. We demonstrate that the proposed robust asymmetric loss performs favorably against the long-tailed with multi-label medical image classification in addition to the various long-tailed single-label datasets. Notably, our method achieves Top-5 results on the CXR-LT dataset of the ICCV CVAMD 2023 competition. We opensource our implementation of the robust asymmetric loss in the public repository: https://github.com/kalelpark/RALoss.
Language
eng
URI
https://aurora.ajou.ac.kr/handle/2018.oak/36950
https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85182937924&origin=inward
DOI
https://doi.org/10.1109/iccvw60793.2023.00286
Journal URL
http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=10350357
Type
Conference
Show full item record

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

Related Researcher

Ryu, Jongbin Image
Ryu, Jongbin유종빈
Department of Software and Computer Engineering
Read More

Total Views & Downloads

File Download

  • There are no files associated with this item.