We propose average Localization-Recall-Precision (aLRP), a unified, bounded, balanced and ranking-based loss function for both classification and localisation tasks in object detection. aLRP extends the Localization-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 $\sim 6$ hyperparameters in the loss functions of state-of-the-art detectors, aLRP has only one hyperparameter, which we did not tune in practice. On the COCO dataset, aLRP improves its ranking-based predecessor, AP Loss, more than $4$ AP points and outperforms all one-stage detectors. The code is available at: https://github.com/kemaloksuz/aLRPLoss .
Speakers: Kemal Oksuz, Baris Can Cam, Emre Akbas, Sinan Kalkan