Abstract
Weakly supervised semantic segmentation with only image-level labels is an essential application since it reduces the considerable human effort to fully annotate image. Most state-of-the-art methods take into account discriminative regions or prior knowledge (called seeds) by applying the recent Classification Activation Maps (CAM) methods. As seeds used in the CAM methods could be considered as segmentation knowledge, increasing seeds will naturally improve the performance of the CAM methods. We treat such task as a seed exploration with clustering learning, which is different from the current methods in which region mining or seeds learning are performed in an end-to-end learning manner. In this paper, we propose a progressive framework containing autoencoders to explore numerous and accurate seeds to further improve the performance of CAM methods. Our explored seeds can replace the initial seeds, and thus, they can be integrated with current weakly supervised semantic segmentation methods for performance improvement. We show experimentally that our provided seeds lead to better model training. As a result, we obtain performance improvement from corresponding counterparts to reach 68.1 and 69.2% mIoU on PASCAL VOC 2012 validation and test dataset, respectively.
Similar content being viewed by others
Data availability statement
The images in this study were taken from the publicly dataset, The PASCAL Visual Object Classes Challenge 2012, http://host.robots.ox.ac.uk/pascal/VOC/voc2012/.
Notes
The source code is available for reviewers and will be made public after publication http://www.yiminyang.com/weakly_supervised.html.
References
Dai J, He K, Sun J (2015) Boxsup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 1635–1643
Lin D, Dai J, Jia J, He K, Sun J (2016) Scribblesup: scribble-supervised convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3159–3167
Bearman A, Russakovsky O, Ferrari V, Fei-Fei L (2016) What’s the point: semantic segmentation with point supervision. In: European conference on computer vision, pp 549–565, Springer
Kolesnikov A, Lampert CH (2016) Seed, expand and constrain: three principles for weakly-supervised image segmentation. In: European conference on computer vision, pp 695–711, Springer
Huang Z, Wang X, Wang J, Liu W, Wang J (2018) Weakly-supervised semantic segmentation network with deep seeded region growing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7014–7023
Fan J, Zhang Z, Tan T, Song C, Xiao J (2020) Cian: cross-image affinity net for weakly supervised semantic segmentation. In: Proceedings of the AAAI conference on artificial intelligence 34:10762–10769
Sun G, Wang W, Dai J, Van Gool L (2020) Mining cross-image semantics for weakly supervised semantic segmentation. In: European conference on computer vision, pp 347–365. Springer
Zhou B, Khosla A, Lapedriza A, Oliva A, Torralba A (2016) Learning deep features for discriminative localization. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2921–2929
Singh KK, Lee YJ (2017) Hide-and-seek: forcing a network to be meticulous for weakly-supervised object and action localization. In: 2017 IEEE international conference on computer vision (ICCV), pp 3544–3553, IEEE
Wei Y, Feng J, Liang X, Cheng M-M, Zhao Y, Yan S (2017) Object region mining with adversarial erasing: a simple classification to semantic segmentation approach. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1568–1576
Li K, Wu Z, Peng K-C, Ernst J, Fu Y (2018) Tell me where to look: guided attention inference network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 9215–9223
Chaudhry A, Dokania PK, Torr PH (2017) Discovering class-specific pixels for weakly-supervised semantic segmentation. arXiv preprint arXiv:1707.05821
Hou Q, Jiang P-T, Wei Y, Cheng M-M (2018) Self-erasing network for integral object attention. arXiv preprint arXiv:1810.09821
Zhang X, Wei Y, Feng J, Yang Y, Huang TS (2018) Adversarial complementary learning for weakly supervised object localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 1325–1334
Oh SJ, Benenson R, Khoreva A, Akata Z, Fritz M, Schiele B (2017) Exploiting saliency for object segmentation from image level labels. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 5038–5047, IEEE
Ahn J, Kwak S (2018) Learning pixel-level semantic affinity with image-level supervision for weakly supervised semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4981–4990
Lee J, Choi J, Mok J, Yoon S (2021) Reducing information bottleneck for weakly supervised semantic segmentation. arXiv:2110.06530 [cs]
Zhang F, Gu C, Zhang C, Dai Y (2021) Complementary patch for weakly supervised semantic segmentation. arXiv:2108.03852 [cs]
Chen Q, Yang L, Lai J, Xie X (2022) Self-supervised image-specific prototype exploration for weakly supervised semantic segmentation. arXiv:2203.02909 [cs]
Chen Z, Wang T, Wu X, Hua X-S, Zhang H, Sun Q (2022) Class re-activation maps for weakly-supervised semantic segmentation. arXiv:2203.00962 [cs]
Lee M, Kim D, Shim H (2022) Threshold matters in WSSS: manipulating the activation for the Robust and accurate segmentation model against thresholds. arXiv:2203.16045 [cs]
Rumelhart DE, Hinton GE, Williams RJ (1985) Learning internal representations by error propagation. Tech. rep. California Univ San Diego La Jolla Inst for Cognitive Science
Yang Y, Wang Y, Jonathan Wu QM, Lin X, Liu M (2015) Progressive learning machine: a new approach for general hybrid system approximation. IEEE Trans Neural Netw Learn Syst 26(9):1855–1874
MacQueen J et al (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol 1, pp 281–297, Oakland, CA, USA
Fukunaga K, Hostetler L (1975) The estimation of the gradient of a density function, with applications in pattern recognition. IEEE Trans Inf Theory 21(1):32–40
Everingham M, Eslami SA, Van Gool L, Williams CK, Winn J, Zisserman A (2015) The pascal visual object classes challenge: a retrospective. Int J Comput Vis 111(1):98–136
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556
Yang Y, Wu QJ, Wang Y (2016) Autoencoder with invertible functions for dimension reduction and image reconstruction. IEEE Trans Syst Man Cybernet Syst 48(7):1065–1079
Miyato T, Maeda S-I, Koyama M, Ishii S (2018) Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE Trans Pattern Anal Mach Intell 41(8):1979–1993
Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A (2010) The pascal visual object classes (voc) challenge. Int J Comput Vis 88(2):303–338
Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2014) Semantic image segmentation with deep convolutional nets and fully connected crfs. arXiv preprint arXiv:1412.7062
Hariharan B, Arbeláez P, Bourdev L, Maji S, Malik J (2011) Semantic contours from inverse detectors. In: 2011 International Conference on Computer Vision, pp 991–998, IEEE
Chan L, Hosseini MS, Plataniotis KN (2021) A comprehensive analysis of weakly-supervised semantic segmentation in different image domains.Int J Comput Vis 129(2):361–384
Lee J, Kim E, Lee S, Lee J, Yoon S (2019) Ficklenet: Weakly and semi-supervised semantic image segmentation using stochastic inference. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 5267–5276
Xu L, Xue H, Bennamoun M, Boussaid F, Sohel F (2021) Atrous convolutional feature network for weakly supervised semantic segmentation. Neurocomputing 421:115–126
Wei Y, Liang X, Chen Y, Shen X, Cheng M-M, Feng J, Zhao Y, Yan S (2016) Stc: a simple to complex framework for weakly-supervised semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(11):2314–2320
Hong S, Yeo D, Kwak S, Lee H, Han B (2017) Weakly supervised semantic segmentation using web-crawled videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 7322–7330
Pinheiro PO, Collobert R (2015) From image-level to pixel-level labeling with convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1713–1721
Papandreou G, Chen L-C, Murphy KP, Yuille AL (2015) Weakly-and semi-supervised learning of a deep convolutional network for semantic image segmentation. In: Proceedings of the IEEE international conference on computer vision, pp 1742–1750
Wang X, You S, Li X, Ma H (2018) Weakly-supervised semantic segmentation by iteratively mining common object features. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1354–1362
Liu J, Yu C, Yang B, Gao C, Sang N (2020) Csenet: cascade semantic erasing network for weakly-supervised semantic segmentation. Neurocomputing
Li Y, Liu Y, Liu G, Guo M (2020) Weakly supervised semantic segmentation by iterative superpixel-crf refinement with initial clues guiding. Neurocomputing 391:25–41
Wang Y, Zhang J, Kan M, Shan S, Chen X (2020) Self-supervised equivariant attention mechanism for weakly supervised semantic segmentation. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pp 12275–12284
Chang Y-T, Wang Q, Hung W-C, Piramuthu R, Tsai Y-H, Yang M-H (2020) Weakly-supervised semantic segmentation via sub-category exploration. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 8991–9000
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chow, T., Deng, H., Yang, Y. et al. Explored seeds generation for weakly supervised semantic segmentation. Neural Comput & Applic 36, 1007–1022 (2024). https://doi.org/10.1007/s00521-023-09073-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-023-09073-z