Presentation information

General Session

General Session » GS-7 Vision, speech media processing

[4I3-GS-7d] 画像音声メディア処理:画像理解

Fri. Jun 11, 2021 1:40 PM - 3:20 PM Room I (GS room 4)

座長:吉田 周平(NEC)

2:40 PM - 3:00 PM

[4I3-GS-7d-04] Multi-class Semantic Segmentation by Optimized Class Probability Matrix

〇Sota Kato1, Kazuhiro Hotta1 (1. Meijo University)

Keywords: Image recognition, Deep Learning, Semantic Segmentation

In semantic segmentation, where all pixels in an image are labeled, CNN is known to produce highly accurate results, and it has been applied to automated driving techniques. Cross Entropy Loss is often used for learning semantic segmentation, and Intersection over Union (IoU) is often used as its evaluation metric. In order to achieve more accurate prediction, loss functions that directly optimize the IoU have been studied in recent years. However, almost of the previous studies have shown the effectiveness only in the case of two-class segmentation, and few studies have confirmed the effectiveness in multi-class segmentation. In this study, we propose a new loss function that improves the accuracy of the IoU by optimizing the matrix composed of class probabilities. The effectiveness of the proposed method is confirmed by experiments on two-class and multi-class segmentation.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.