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
  • [1] Semantic Segmentation via Multi-task, Multi-domain Learning
    Fourure, Damien
    Emonet, Remi
    Fromont, Elisa
    Muselet, Damien
    Tremeau, Alain
    Wolf, Christian
    STRUCTURAL, SYNTACTIC, AND STATISTICAL PATTERN RECOGNITION, S+SSPR 2016, 2016, 10029 : 333 - 343
  • [2] AdvNet: Multi-Task Fusion of Object Detection and Semantic Segmentation
    Liu, Xiaohan
    Wang, Heng
    2019 CHINESE AUTOMATION CONGRESS (CAC2019), 2019, : 3359 - 3362
  • [3] Multi-scale Field Distillation for Multi-task Semantic Segmentation
    Dong, Aimei
    Liu, Sidi
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT II, 2023, 14255 : 508 - 519
  • [4] A Multi-Task Model for Pulmonary Nodule Segmentation and Classification
    Tang, Tiequn
    Zhang, Rongfu
    JOURNAL OF IMAGING, 2024, 10 (09)
  • [5] Efficient multi-task progressive learning for semantic segmentation and disparity estimation
    Cuevas-Velasquez, Hanz
    Galan-Cuenca, Alejandro
    Fisher, Robert B.
    Gallego, Antonio Javier
    PATTERN RECOGNITION, 2024, 154
  • [6] A Multi-task Learning Framework for Semantic Segmentation in MLS Point Clouds
    Lin, Xi
    Luo, Huan
    Guo, Wenzhong
    Wang, Cheng
    Li, Jonathan
    ARTIFICIAL INTELLIGENCE AND SECURITY, ICAIS 2022, PT I, 2022, 13338 : 382 - 392
  • [7] SEMANTIC SEGMENTATION AND CHANGE DETECTION BY MULTI-TASK U-NET
    Tsutsui, Shungo
    Hirakawa, Tsubasa
    Yamashita, Takayoshi
    Fujiyoshi, Hironobu
    2021 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2021, : 619 - 623
  • [8] Multi-task learning for gland segmentation
    Rezazadeh, Iman
    Duygulu, Pinar
    SIGNAL IMAGE AND VIDEO PROCESSING, 2023, 17 (01) : 1 - 9
  • [9] Multi-Task Learning for Subspace Segmentation
    Wang, Yu
    Wipf, David
    Ling, Qing
    Chen, Wei
    Wassell, Ian
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 37, 2015, 37 : 1209 - 1217
  • [10] Multi-task learning for gland segmentation
    Iman Rezazadeh
    Pinar Duygulu
    Signal, Image and Video Processing, 2023, 17 : 1 - 9