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
  • [41] Multi-task Learning of Semantic Segmentation and Height Estimation for Multi-modal Remote Sensing Images
    Mengyu WANG
    Zhiyuan YAN
    Yingchao FENG
    Wenhui DIAO
    Xian SUN
    Journal of Geodesy and Geoinformation Science, 2023, 6 (04) : 27 - 39
  • [42] Semantic Communication Approach for Multi-Task Image Transmission
    Zhang, Zhenguo
    Yang, Qianqian
    He, Shibo
    Shi, Zhiguo
    2022 IEEE 96TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2022-FALL), 2022,
  • [43] MULTI-MODAL MULTI-TASK LEARNING FOR SEMANTIC SEGMENTATION OF LAND COVER UNDER CLOUDY CONDITIONS
    Xu, Fang
    Shi, Yilei
    Yang, Wen
    Zhu, Xiaoxiang
    IGARSS 2023 - 2023 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2023, : 6274 - 6277
  • [44] Weakly Supervised Multi-task Learning for Semantic Parsing
    Shao, Bo
    Gong, Yeyun
    Bao, Junwei
    Ji, Jianshu
    Cao, Guihong
    Lin, Xiaola
    Duan, Nan
    PROCEEDINGS OF THE TWENTY-EIGHTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2019, : 3375 - 3381
  • [45] Monocular Outdoor Semantic Mapping with a Multi-task Network
    Bai, Yucai
    Fan, Lei
    Pan, Ziyu
    Chen, Long
    2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2019, : 1992 - 1997
  • [46] An Empirical Study of Multi-Task Learning on BERT for Biomedical Text Mining
    Peng, Yifan
    Chen, Qingyu
    Lu, Zhiyong
    19TH SIGBIOMED WORKSHOP ON BIOMEDICAL LANGUAGE PROCESSING (BIONLP 2020), 2020, : 205 - 214
  • [47] Improvements on a Multi-task BERT Model
    Agrali, Mahmut
    Tekir, Selma
    32ND IEEE SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE, SIU 2024, 2024,
  • [48] Multi-task agency: a combinatorial model
    Bardsley, P
    JOURNAL OF ECONOMIC BEHAVIOR & ORGANIZATION, 2001, 44 (02) : 233 - 248
  • [49] Multi-task Pre-training Language Model for Semantic Network Completion
    Li, Da
    Zhu, Boqing
    Yang, Sen
    Xu, Kele
    Yi, Ming
    He, Yukai
    Wang, Huaimin
    ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2023, 22 (11)
  • [50] Multi-task Learning Based Keywords Weighted Siamese Model for Semantic Retrieval
    Kuang, Mengmeng
    Chen, Zhenhong
    Wang, Weiyan
    Kang, Lie
    Yan, Qiang
    Tang, Min
    Hao, Penghui
    ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2023, PT III, 2023, 13937 : 86 - 98