• 대한전기학회
Mobile QR Code QR CODE : The Transactions of the Korean Institute of Electrical Engineers
  • COPE
  • kcse
  • 한국과학기술단체총연합회
  • 한국학술지인용색인
  • Scopus
  • crossref
  • orcid
Title Dynamic Fusion Method of Loss Functions for Unbiased Object Detection in Long-tailed Datasets
Authors 김정현(Jeonghyeon Kim) ; 김한솔(Han Sol Kim) ; 이창은(Changeun Lee) ; 이광일(Kwangil Lee)
DOI https://doi.org/10.5370/KIEE.2026.75.6.1400
Page pp.1400-1405
Keywords Long-tail Dataset; Real-time Object Detection; Dynamic Fusion; Class Imbalance
Abstract In this paper, we propose a dynamic fusion method that combines varifocal loss (VFL) and seesaw loss (SSL) to address the class imbalance problem in long-tail datasets for object detection models. The static combination of two loss functions makes the training unstable due to the noisy gradients of the SSL, which interrupt the IoU-aware classification flow and limit overall performance. To address this problem, we aim to effectively mitigate the biased learning problem in long-tailed datasets by maintaining the stability of IoU-aware classification during the early learning stages and gradually reflecting the calibration effect of the SSL in the latter stages of training. Finally, we validate unbiased detecting performance of the object detection on the LVIS dataset. To this end, we applied the proposed loss fusion method to the RT-DETRv2 model, resulting in 35.4% of bias mitigation for rare classes.