Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task

被引:4
|
作者
Saire, Darwin [1 ]
Rivera, Adin Ramirez [1 ]
机构
[1] Univ Estadual Campinas, Inst Comp, BR-13083852 Campinas, Brazil
基金
巴西圣保罗研究基金会;
关键词
Task analysis; Feature extraction; Image segmentation; Semantics; Image edge detection; Computers; Computational modeling; Explainable latent spaces; multi-task learning; semantic segmentation; DEEP; IMAGE; VIDEO;
D O I
10.1109/ACCESS.2021.3085218
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The semantic segmentation (SS) task aims to create a dense classification by labeling at the pixel level each object present on images. Convolutional neural network (CNN) approaches have been widely used, and exhibited the best results in this task. However, the loss of spatial precision on the results is a main drawback that has not been solved. In this work, we propose to use a multi-task approach by complementing the semantic segmentation task with edge detection, semantic contour, and distance transform tasks. We propose that by sharing a common latent space, the complementary tasks can produce more robust representations that can enhance the semantic labels. We explore the influence of contour-based tasks on latent space, as well as their impact on the final results of SS. We demonstrate the effectiveness of learning in a multi-task setting for hourglass models in the Cityscapes, CamVid, and Freiburg Forest datasets by improving the state-of-the-art without any refinement post-processing.
引用
收藏
页码:80654 / 80670
页数:17
相关论文
共 50 条
  • [31] Joint multi-task cascade for instance segmentation
    Wen, Yaole
    Hu, Fuyuan
    Ren, Jinchang
    Shang, Xinru
    Li, Linyan
    Xi, Xuefeng
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2020, 17 (06) : 1983 - 1989
  • [32] DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model
    Gu, Xiuye
    Cui, Yin
    Huang, Jonathan
    Rashwan, Abdullah
    Yang, Xuan
    Zhou, Xingyi
    Ghiasi, Golnaz
    Kuo, Weicheng
    Chen, Huizhong
    Chen, Liang-Chieh
    Ross, David
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [33] Multi-task gradient descent for multi-task learning
    Lu Bai
    Yew-Soon Ong
    Tiantian He
    Abhishek Gupta
    Memetic Computing, 2020, 12 : 355 - 369
  • [34] Multi-task gradient descent for multi-task learning
    Bai, Lu
    Ong, Yew-Soon
    He, Tiantian
    Gupta, Abhishek
    MEMETIC COMPUTING, 2020, 12 (04) : 355 - 369
  • [35] Multi-task Learning to Improve Semantic Segmentation of CBCT Scans using Image Reconstruction
    Tschuchnig, Maximilian E.
    Coste-Marin, Julia
    Steininger, Philipp
    Gadermayr, Michael
    BILDVERARBEITUNG FUR DIE MEDIZIN 2024, 2024, : 243 - 248
  • [36] Guided Multi-task Lane Line Detection with Road-Object Semantic Segmentation
    Tran-Nhat-Minh Ta
    Van-Ho Tran
    Thanh Danh Phan
    Cuong Le
    Van-Hoang-Anh Phan
    My-Ha Le
    COMPUTATIONAL INTELLIGENCE METHODS FOR GREEN TECHNOLOGY AND SUSTAINABLE DEVELOPMENT, GTSD2024, VOL 1, 2024, 1195 : 27 - 40
  • [37] A Multi-Task Convolutional Neural Network for Semantic Segmentation and Event Detection in Laparoscopic Surgery
    Marullo, Giorgia
    Tanzi, Leonardo
    Ulrich, Luca
    Porpiglia, Francesco
    Vezzetti, Enrico
    JOURNAL OF PERSONALIZED MEDICINE, 2023, 13 (03):
  • [38] Deep multi-task learning for a geographically-regularized semantic segmentation of aerial images
    Volpi, Michele
    Tuia, Devis
    ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2018, 144 : 48 - 60
  • [39] A loss-balanced multi-task model for simultaneous detection and segmentation
    Zhang, Wenwen
    Wang, Kunfeng
    Wang, Yutong
    Yan, Lan
    Wang, Fei-Yue
    NEUROCOMPUTING, 2021, 428 : 65 - 78
  • [40] A Weakly Supervised Multi-task Ranking Framework for Actor-Action Semantic Segmentation
    Yan, Yan
    Xu, Chenliang
    Cai, Dawen
    Corso, Jason J.
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2020, 128 (05) : 1414 - 1432