Using different loss functions with YOLACT++ for real-time instance segmentation

Name: Using different loss functions with YOLACT++ for real-time instance segmentation
Author: Köleş, Selin, Karakaş, Selami, Ndigande, Alain Patrick, Özer, Sedat

İsim	Using different loss functions with YOLACT++ for real-time instance segmentation
Yazar	Köleş, Selin, Karakaş, Selami, Ndigande, Alain Patrick, Özer, Sedat
Basım Tarihi:	2023
Basım Yeri	- IEEE
Konu	Instance segmentation, Loss function, Real time segmentation, YOLACT++
Tür	Belge
Dil	İngilizce
Dijital	Evet
Yazma	Hayır
Kütüphane:	Özyeğin Üniversitesi
Demirbaş Numarası	979-835030396-4
Kayıt Numarası	6829a854-3d5f-476c-bc9f-9cf7ef949a73
Lokasyon	Computer Science
Tarih	2023
Örnek Metin	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.
DOI	10.1109/TSP59544.2023.10197832

Kaynağa git Özyeğin Üniversitesi

Aramaya Dön

Özyeğin Üniversitesi

Kaynağa git

Using different loss functions with YOLACT++ for real-time instance segmentation

Yazar Köleş, Selin, Karakaş, Selami, Ndigande, Alain Patrick, Özer, Sedat

Basım Tarihi 2023

Basım Yeri - IEEE

Konu Instance segmentation, Loss function, Real time segmentation, YOLACT++

Tür Belge

Dil İngilizce

Dijital Evet

Yazma Hayır

Kütüphane Özyeğin Üniversitesi

Demirbaş Numarası 979-835030396-4

Kayıt Numarası 6829a854-3d5f-476c-bc9f-9cf7ef949a73

Lokasyon Computer Science

Tarih 2023

Örnek Metin 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.

DOI 10.1109/TSP59544.2023.10197832