Using different loss functions with YOLACT++ for real-time instance segmentation
Published in In the proceedings of 2023 46th International Conference on Telecommunications and Signal Processing (TSP), 2023
Download paper here Use Google Scholar for full citation
In this paper, we study and analyze the performance of various loss functions on a recently proposed real-time instance segmentation algorithm, YOLACT++. In particular, we study the loss functions, including Huber Loss, Binary Cross Entropy (BCE), Mean Square Error (MSE), Log-Cosh-Dice Loss, and their various combinations within the YOLACT++ architecture. We demonstrate that we can use different loss functions from the default loss function (BCE) of YOLACT++ for improved real-time segmentation results. In our experiments, we show that a certain combination of two loss functions improves the segmentation performance of YOLACT++ in terms of the mean Average Precision (mAP) metric on Cigarettes dataset, when compared to its original loss function.
Recommended citation: Koles, S., Karakas, S., Ndigande, A.P. and Ozer, S., 2023, July. Using different loss functions with YOLACT++ for real-time instance segmentation. In 2023 46th International Conference on Telecommunications and Signal Processing (TSP) (pp. 264-267). IEEE.