A Ranking-based, Balanced Loss Function Unifying Classification and Localisation in Object Detection


Creative Commons License

Öksüz K., Çam B. C., Akbaş E., Kalkan S.

2020 Conference on Neural Information Processing Systems, Montreal, Canada, 6 - 12 December 2020, vol.33, pp.15534-15545

  • Publication Type: Conference Paper / Full Text
  • Volume: 33
  • City: Montreal
  • Country: Canada
  • Page Numbers: pp.15534-15545
  • Middle East Technical University Affiliated: Yes

Abstract

We propose average Localisation-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. aLRP extends the Localisation-Recall-Precision (LRP) performance metric (Oksuz et al., 2018) inspired from how Average Precision (AP) Loss extends precision to a ranking-based loss function for classification (Chen et al., 2020). aLRP has the following distinct advantages: (i) aLRP is the first ranking-based loss function for both classification and localisation tasks. (ii) Thanks to using ranking for both tasks, aLRP naturally enforces high-quality localisation for high-precision classification. (iii) aLRP provides provable balance between positives and negatives. (iv) Compared to on average ~6 hyperparameters in the loss functions of state-of-the-art detectors, aLRP Loss has only one hyperparameter, which we did not tune in practice. On the COCO dataset, aLRP Loss improves its ranking-based predecessor, AP Loss, up to around 5 AP points, achieves 48.9 AP without test time augmentation and outperforms all one-stage detectors. Code available at: https://github.com/kemaloksuz/aLRPLoss .