skip to main content
10.1145/3633637.3633697acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiccprConference Proceedingsconference-collections
research-article

Exploring Non-Significant Areas for Weakly Supervised Semantic Segmentation

Published: 28 February 2024 Publication History

Abstract

Semantic segmentation is the process of categorizing all pixels in an image. Given the inherent challenges of attaining fine labels, researchers have recently embraced weak labels to mitigate the annotation burden of segmentation. The current work on weakly supervised semantic segmentation (WSSS) mainly focuses on expanding pseudo-label seeds in the salient regions of the image, but there are also many objects outside the salient area that have not been discovered. In this work, we propose an innovative WSSS method by exploring non-significant areas (ENSA). Specifically, we first utilize multiple local views that are randomly clipped from the input image to extract attention. Then, we design a local-global knowledge transfer module (LGKT) for the global network so that the global network can obtain the complementary attention knowledge of multiple local attention maps through online learning to produce high-quality attention maps. To further explore the non-significant areas of complex images, we adopt a NSRM module to generate masked labels. Comprehensive experiments on the PASCAL VOC 2012 dataset illustrate that we achieve state-of-the-art performance compared to existing work.

References

[1]
S. Bhadoria, P. Aggarwal, C. Dethe, and R. Vig, “Comparison of segmentation tools for multiple modalities in medical imaging,” Journal of advances in information technology, vol. 3, no. 4, pp. 197-205, 2012.
[2]
B. Hariharan, P. Arbeláez, L. Bourdev, S. Maji, and J. Malik, "Semantic contours from inverse detectors." pp. 991-998.
[3]
L. Ru, H. Zheng, Y. Zhan, and B. Du, "Token contrast for weakly-supervised semantic segmentation." pp. 3093-3102.
[4]
F. F. Wahid, G. Raju, S. M. Joseph, D. Swain, O. P. Das, and B. Acharya, “A Novel Fuzzy-Based Thresholding Approach for Blood Vessel Segmentation from Fundus Image,” Journal of Advances in Information Technology, vol. 14, no. 2, 2023.
[5]
A. Bearman, O. Russakovsky, V. Ferrari, and L. Fei-Fei, "What's the point: Semantic segmentation with point supervision." pp. 549-565.
[6]
C. Song, Y. Huang, W. Ouyang, and L. Wang, "Box-driven class-wise region masking and filling rate guided loss for weakly supervised semantic segmentation." pp. 3136-3145.
[7]
D. Lin, J. Dai, J. Jia, K. He, and J. Sun, "Scribblesup: Scribble-supervised convolutional networks for semantic segmentation." pp. 3159-3167.
[8]
P. O. Pinheiro, and R. Collobert, "From image-level to pixel-level labeling with convolutional networks." pp. 1713-1721.
[9]
B. Zhou, A. Khosla, A. Lapedriza, A. Oliva, and A. Torralba, "Learning deep features for discriminative localization." pp. 2921-2929.
[10]
Z. Huang, X. Wang, J. Wang, W. Liu, and J. Wang, "Weakly-supervised semantic segmentation network with deep seeded region growing." pp. 7014-7023.
[11]
A. Kolesnikov, and C. H. Lampert, "Seed, expand and constrain: Three principles for weakly-supervised image segmentation." pp. 695-711.
[12]
P.-T. Jiang, L.-H. Han, Q. Hou, M.-M. Cheng, and Y. Wei, “Online attention accumulation for weakly supervised semantic segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 10, pp. 7062-7077, 2021.
[13]
P.-T. Jiang, Q. Hou, Y. Cao, M.-M. Cheng, Y. Wei, and H.-K. Xiong, "Integral object mining via online attention accumulation." pp. 2070-2079.
[14]
J. Chen, W. Lu, Y. Li, L. Shen, and J. Duan, “Adversarial Learning of Object-Aware Activation Map for Weakly-Supervised Semantic Segmentation,” IEEE Transactions on Circuits and Systems for Video Technology, 2023.
[15]
J. Lee, E. Kim, and S. Yoon, "Anti-adversarially manipulated attributions for weakly and semi-supervised semantic segmentation." pp. 4071-4080.
[16]
X. Zhang, Y. Wei, J. Feng, Y. Yang, and T. S. Huang, "Adversarial complementary learning for weakly supervised object localization." pp. 1325-1334.
[17]
Y. Yao, T. Chen, G.-S. Xie, C. Zhang, F. Shen, Q. Wu, Z. Tang, and J. Zhang, "Non-salient region object mining for weakly supervised semantic segmentation." pp. 2623-2632.
[18]
J. Ahn, and S. Kwak, "Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation." pp. 4981-4990.
[19]
S. Lee, M. Lee, J. Lee, and H. Shim, "Railroad is not a train: Saliency as pseudo-pixel supervision for weakly supervised semantic segmentation." pp. 5495-5505.
[20]
Z. Wu, C. Shen, and A. Van Den Hengel, “Wider or deeper: Revisiting the resnet model for visual recognition,” Pattern Recognition, vol. 90, pp. 119-133, 2019.
[21]
Y. Wang, J. Zhang, M. Kan, S. Shan, and X. Chen, "Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation." pp. 12275-12284.
[22]
Y.-T. Chang, Q. Wang, W.-C. Hung, R. Piramuthu, Y.-H. Tsai, and M.-H. Yang, "Weakly-supervised semantic segmentation via sub-category exploration." pp. 8991-9000.
[23]
Q. Yao, and X. Gong, “Saliency guided self-attention network for weakly and semi-supervised semantic segmentation,” IEEE Access, vol. 8, pp. 14413-14423, 2020.
[24]
J. Lee, E. Kim, S. Lee, J. Lee, and S. Yoon, "Ficklenet: Weakly and semi-supervised semantic image segmentation using stochastic inference." pp. 5267-5276.
[25]
L. Chen, W. Wu, C. Fu, X. Han, and Y. Zhang, "Weakly supervised semantic segmentation with boundary exploration." pp. 347-362.
[26]
B. Kim, S. Han, and J. Kim, "Discriminative region suppression for weakly-supervised semantic segmentation." pp. 1754-1761.
[27]
X. Li, T. Zhou, J. Li, Y. Zhou, and Z. Zhang, "Group-wise semantic mining for weakly supervised semantic segmentation." pp. 1984-1992.
[28]
Y. Su, R. Sun, G. Lin, and Q. Wu, "Context decoupling augmentation for weakly supervised semantic segmentation." pp. 7004-7014.
[29]
J. Xie, X. Hou, K. Ye, and L. Shen, "Clims: Cross language image matching for weakly supervised semantic segmentation." pp. 4483-4492.
[30]
P.-T. Jiang, Y. Yang, Q. Hou, and Y. Wei, "L2g: A simple local-to-global knowledge transfer framework for weakly supervised semantic segmentation." pp. 16886-16896.

Index Terms

  1. Exploring Non-Significant Areas for Weakly Supervised Semantic Segmentation

    Recommendations

    Comments

    Information & Contributors

    Information

    Published In

    cover image ACM Other conferences
    ICCPR '23: Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition
    October 2023
    589 pages
    ISBN:9798400707988
    DOI:10.1145/3633637
    Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

    Publisher

    Association for Computing Machinery

    New York, NY, United States

    Publication History

    Published: 28 February 2024

    Permissions

    Request permissions for this article.

    Check for updates

    Author Tags

    1. Deep learning
    2. Exploring non-significant areas
    3. Semantic segmentation
    4. Weakly supervised learning

    Qualifiers

    • Research-article
    • Research
    • Refereed limited

    Conference

    ICCPR 2023

    Contributors

    Other Metrics

    Bibliometrics & Citations

    Bibliometrics

    Article Metrics

    • 0
      Total Citations
    • 17
      Total Downloads
    • Downloads (Last 12 months)17
    • Downloads (Last 6 weeks)4
    Reflects downloads up to 20 Feb 2025

    Other Metrics

    Citations

    View Options

    Login options

    View options

    PDF

    View or Download as a PDF file.

    PDF

    eReader

    View online with eReader.

    eReader

    HTML Format

    View this article in HTML Format.

    HTML Format

    Figures

    Tables

    Media

    Share

    Share

    Share this Publication link

    Share on social media