On Power Jaccard Losses for Semantic Segmentation

被引：20

作者：

Duque-Arias, David ^{[1
]}

Velasco-Forero, Santiago ^{[1
]}

Deschaud, Jean-Emmanuel ^{[1
]}

Goulette, Francois ^{[1
]}

Serna, Andres ^{[2
]}

Decenciere, Etienne ^{[1
]}

Marcotegui, Beatriz ^{[1
]}

机构：

[1] PSL Res Univ, MINES ParisTech, Paris, France

[2] Terra3D Res, Paris, France

来源：

VISAPP: PROCEEDINGS OF THE 16TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS - VOL. 5: VISAPP | 2021年

关键词：

Loss Functions; Image Segmentation; Jaccard Loss; Deep Learning; U-Net Architecture;

D O I：

10.5220/0010304005610568

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this work, a new generalized loss function is proposed called power Jaccard to perform semantic segmentation tasks. It is compared with classical loss functions in different scenarios, including gray level and color image segmentation, as well as 3D point cloud segmentation. The results show improved performance, stability and convergence. We made available the code with our proposal with a demonstrative example.

引用

页码：561 / 568

页数：8

共 50 条

[21] Optimizing the Dice Score and Jaccard Index for Medical Image Segmentation: Theory and Practice
Bertels, Jeroen
Eelbode, Tom
Berman, Maxim
Vandermeulen, Dirk
Maes, Frederik
Bisschops, Raf
Blaschko, Matthew B.
MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2019, PT II, 2019, 11765 : 92 - 100
[22] Lightweight Low-Power U-Net Architecture for Semantic Segmentation
Modiboyina, Chaitanya
Chakrabarti, Indrajit
Ghosh, Soumya Kanti
CIRCUITS SYSTEMS AND SIGNAL PROCESSING, 2024, : 2527 - 2561
[23] LOW-POWER SEMANTIC SEGMENTATION ON EMBEDDED SYSTEMS FOR TRAFFIC IN ASIAN COUNTRIES
Wang, Jun-Long
2022 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO WORKSHOPS (IEEE ICMEW 2022), 2022,
[24] Semantic Relocation Parallel Network for Semantic Segmentation
Chen S.
Xu L.
Zou B.
Chen J.
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2022, 34 (03): : 373 - 381
[25] Class semantic enhancement network for semantic segmentation
Fu, Siming
Wang, Hualiang
Hu, Haoji
He, Xiaoxuan
Long, Yongwen
Bai, Jianhong
Ou, Yangtao
Huang, Yuanjia
Zhou, Mengqiu
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2023, 96
[26] A semantic-based variables selection for ontology learning Taking Jaccard alignment as case
Choukri, Djellali
5TH INTERNATIONAL CONFERENCE ON EMERGING UBIQUITOUS SYSTEMS AND PERVASIVE NETWORKS / THE 4TH INTERNATIONAL CONFERENCE ON CURRENT AND FUTURE TRENDS OF INFORMATION AND COMMUNICATION TECHNOLOGIES IN HEALTHCARE / AFFILIATED WORKSHOPS, 2014, 37 : 56 - 63
[27] Automatic Skin Lesion Segmentation Using Deep Fully Convolutional Networks With Jaccard Distance
Yuan, Yading
Chao, Ming
Lo, Yeh-Chi
IEEE TRANSACTIONS ON MEDICAL IMAGING, 2017, 36 (09) : 1876 - 1886
[28] Boosting Semantic Segmentation by Conditioning the Backbone with Semantic Boundaries
Ishikawa, Haruya
Aoki, Yoshimitsu
SENSORS, 2023, 23 (15)
[29] Hierarchical Semantic Contrast for Weakly Supervised Semantic Segmentation
Wu, Yuanchen
Li, Xiaoqiang
Dai, Songmin
Li, Jide
Liu, Tong
Xie, Shaorong
PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 1542 - 1550
[30] Towards Bridging Semantic Gap to Improve Semantic Segmentation
Pang, Yanwei
Li, Yazhao
Shen, Jianbing
Shao, Ling
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 4229 - 4238

← 1 2 3 4 5 →