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
  • [21] A Weakly Supervised Multi-task Ranking Framework for Actor–Action Semantic Segmentation
    Yan Yan
    Chenliang Xu
    Dawen Cai
    Jason J. Corso
    International Journal of Computer Vision, 2020, 128 : 1414 - 1432
  • [22] Instance-aware Semantic Segmentation via Multi-task Network Cascades
    Dai, Jifeng
    He, Kaiming
    Sun, Jian
    2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 3150 - 3158
  • [23] Optimizing multi-task network with learned prototypes for weakly supervised semantic segmentation
    Zhou, Lei
    Wang, Jiasong
    Luo, Jing
    Guo, Yuheng
    Li, Xiaoxiao
    SIGNAL PROCESSING-IMAGE COMMUNICATION, 2025, 134
  • [24] Multi-task Learning for Deep Semantic Hashing
    Ma, Lei
    Li, Hongliang
    Wu, Qingbo
    Shang, Chao
    Ngan, Kingngi
    2018 IEEE INTERNATIONAL CONFERENCE ON VISUAL COMMUNICATIONS AND IMAGE PROCESSING (IEEE VCIP), 2018,
  • [25] An Asynchronous Multi-Task Semantic Communication Method
    Tian, Zhiyi
    Vo, Hiep
    Zhang, Chenhan
    Min, Geyong
    Yu, Shui
    IEEE NETWORK, 2024, 38 (04): : 275 - 283
  • [26] Multi-task Learning by Leveraging the Semantic Information
    Zhou, Fan
    Chaib-draa, Brahim
    Wang, Boyu
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 11088 - 11096
  • [27] Multi-task Learning for Brain Tumor Segmentation
    Weninger, Leon
    Liu, Qianyu
    Merhof, Dorit
    BRAINLESION: GLIOMA, MULTIPLE SCLEROSIS, STROKE AND TRAUMATIC BRAIN INJURIES (BRAINLES 2019), PT I, 2020, 11992 : 327 - 337
  • [28] Joint multi-task cascade for instance segmentation
    Yaole Wen
    Fuyuan Hu
    Jinchang Ren
    Xinru Shang
    Linyan Li
    Xuefeng Xi
    Journal of Real-Time Image Processing, 2020, 17 : 1983 - 1989
  • [29] Multi-task learning framework for echocardiography segmentation
    Monkam, Patrice
    Jin, Songbai
    Lu, Wenkai
    2022 IEEE INTERNATIONAL ULTRASONICS SYMPOSIUM (IEEE IUS), 2022,
  • [30] Multi-task Learning Based Skin Segmentation
    Tan, Taizhe
    Shan, Zhenghao
    KNOWLEDGE SCIENCE, ENGINEERING AND MANAGEMENT, PT III, KSEM 2023, 2023, 14119 : 360 - 369