Back to Search

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

Title	Using different loss functions with YOLACT++ for real-time instance segmentation
Author	Köleş, Selin, Karakaş, Selami, Ndigande, Alain Patrick, Özer, Sedat
Publication Date:	2023
Publication Place	- IEEE
Subject	Instance segmentation, Loss function, Real time segmentation, YOLACT++
Type	Document
Language	English
Digital	Yes
Manuscript	No
Library:	Özyeğin University
Library Asset ID	979-835030396-4
Record ID	6829a854-3d5f-476c-bc9f-9cf7ef949a73
Library Location	Computer Science
Date	2023
Sample Text	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

View in source Özyeğin University Özyeğin University - Historical works, archives, and periodicals search engine

Özyeğin University

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

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

Publication Date 2023

Publication Place - IEEE

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

Type Document

Language English

Digital Yes

Manuscript No

Library Özyeğin University

Library Asset ID 979-835030396-4

Record ID 6829a854-3d5f-476c-bc9f-9cf7ef949a73

Library Location Computer Science

Date 2023

Sample Text 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