Abstract
Weakly supervised object localization mines the pixel-level location information based on image-level annotations. The traditional weakly supervised object localization approaches exploit the last convolutional feature map to locate the discriminative regions with abundant semantics. Although it shows the localization ability of classification network, the process lacks the use of shallow edge and texture features, which cannot meet the requirement of object integrity in the localization task. Thus, we propose a novel shallow feature-driven dual-edges localization (DEL) network, in which dual kinds of shallow edges are utilized to mine entire target object regions. Specifically, we design an edge feature mining (EFM) module to extract the shallow edge details through the similarity measurement between the original class activation map and shallow features. We exploit the EFM module to extract two kinds of edges, named the edge of the shallow feature map and the edge of shallow gradients, for enhancing the edge details of the target object in the last convolutional feature map. The total process is proposed during the inference stage, which does not bring extra training costs. Extensive experiments on both the ILSVRC and CUB-200-2011 datasets show that the DEL method obtains consistency and substantial performance improvements compared with the existing methods.
Similar content being viewed by others
References
I. B. Senkyire, Z. Liu. Supervised and semi-supervised methods for abdominal organ segmentation: A review. International Journal of Automation and Computing, vol.18, no. 6, pp. 887–914, 2021. DOI: https://doi.org/10.1007/s11633-021-1313-0.
X. Y. Zhang, H. C. Shi, C. S. Li, L. X. Duan. TwinNet: Twin structured knowledge transfer network for weakly supervised action localization. Machine Intelligence Research, vol.19, no. 3, pp. 227–246, 2022. DOI: https://doi.org/10.1007/s11633-022-1333-4.
D. W. Zhang, J. W. Han, G. Cheng, M. H. Yang. Weakly supervised object localization and detection: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.44, no.9, pp.5866–5885, 2021. DOI: https://doi.org/10.1109/TPAMI.2021.3074313.
X. L. Zhang, Y. C. Wei, J. S. Feng, Y. Yang, T. Huang. Adversarial complementary learning for weakly supervised object localization. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Salt Lake City, USA, pp. 1325–1334, 2018. DOI: https://doi.org/10.1109/CVPR.2018.00144.
X. L. Zhang, Y. C. Wei, G. L. Kang, Y. Yang, T. Huang. Self-produced guidance for weakly-supervised object localization. In Proceedings of the 15th European Conference on Computer Vision, Springer, Munich, Germany, pp. 610–625, 2018. DOI: https://doi.org/10.1007/978-3-030-01258-8_37.
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra. Grad-CAM: Visual explanations from deep networks via gradient- based localization. In Proceedings of IEEE International Conference on Computer Vision, Venice, Italy, pp. 618–626, 2017. DOI: https://doi.org/10.1109/ICCV.2017.74.
C. C. Tan, G. H. Gu, T. Ruan, S. K. Wei, Y. Zhao. Dualgradients localization framework for weakly supervised object localization. In Proceedings of the 28th ACM International Conference on Multimedia, Seattle, USA, pp. 1976–1984, 2020. DOI: https://doi.org/10.1145/3394171.3413622.
W. J. Hui, C. C. Tan, G. H. Gu, Y. Zhao. Gradient-based refined class activation map for weakly supervised object localization. Pattern Recognition, vol. 128, Article number 108664, 2022. DOI: https://doi.org/10.1016/j.patcog.2022.108664.
C. Y. Li, R. M. Cong, S. Kwong, J. H. Hou, H. Z. Fu, G. P. Zhu, D. W. Zhang, Q. M. Huang. ASIF-Net: Attention steered interweave fusion network for RGB-D salient object detection. IEEE Transactions on Cybernetics, vol.51, no. 1, pp. 88–100, 2021. DOI: https://doi.org/10.1109/TCYB.2020.2969255.
Y. W. Pang, J. L. Cao, X. L. Li. Learning sampling distributions for efficient object detection. IEEE Transactions on Cybernetics, vol.47, no.1, pp. 117–129, 2017. DOI: https://doi.org/10.1109/TCYB.2015.2508603.
J. Z. Peng, H. Kervadec, J. Dolz, I. Ben Ayed, M. Pedersoli, C. Desrosiers. Discretely-constrained deep network for weakly supervised segmentation. Neural Networks, vol.130, pp. 297–308, 2020. DOI: https://doi.org/10.1016/j.neunet.2020.07.011.
R. Girshick, J. Donahue, T. Darrell, J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, pp. 580–587, 2014. DOI: https://doi.org/10.1109/CVPR.2014.81.
K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.37, no.9, pp. 1904–1916, 2015. DOI: https://doi.org/10.1109/TPAMI.2015.2389824.
R. Girshick. Fast R-CNN. In Proceedings of IEEE International Conference on Computer Vision, Santiago, Chile, pp. 1440–1448, 2015. DOI: https://doi.org/10.1109/ICCV.2015.169.
S. Q. Ren, K. M. He, R. Girshick, J. Sun. Faster R-CNN: Towards real-time object detection with region proposal networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, Canada, pp. 91–99, 2015.
J. Redmon, S. Divvala, R. Girshick, A. Farhadi. You only look once: Unified, real-time object detection. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 779–788, 2016. DOI: https://doi.org/10.1109/CVPR.2016.91.
J. Redmon, A. Farhadi. YOLO9000: Better, faster, stronger. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, USA, pp. 6517–65251, 2017. DOI: https://doi.org/10.1109/CVPR.2017.690.
J. Redmon, A. Farhadi. YOLOv3: An incremental improvement, [Online], Available: https://arxiv.org/abs/1804.02767, 2018.
W. Liu, D. Anguelov, D. Erhan, C. Szegedy, S. Reed, C. Y. Fu, A. C. Berg. SSD: Single shot multibox detector. In Proceedings of the 14th European Conference on Computer Vision, Springer, Amsterdam, The Netherlands, pp. 21–37, 2016. DOI: https://doi.org/10.1007/978-3-319-46448-0_2.
S. Bonechi, M. Bianchini, F. Scarselli, P. Andreini. Weak supervision for generating pixel-level annotations in scene text segmentation. Pattern Recognition Letters, vol. 138, pp. 1–7, 2020. DOI: https://doi.org/10.1016/j.patrec.2020.06.023.
F. D. Sun, W. H. Li. Saliency guided deep network for weakly-supervised image segmentation. Pattern Recognition Letters, vol.120, pp.62–68, 2019. DOI: https://doi.org/10.1016/j.patrec.2019.01.009.
X. L. Zhang, Y. C. Wei, Y. Yang, F. Wu. Rethinking localization map: Towards accurate object perception with self-enhancement maps, [Online], Available: https://arxiv.org/abs/2006.05220, 2020.
W. Bae, J. Noh, G. Kim. Rethinking class activation mapping for weakly supervised object localization. In Proceedings of the 16th European Conference on Computer Vision, Springer, Glasgow, UK, pp. 618–634, 2020. DOI: https://doi.org/10.1007/978-3-030-58555-6_37.
B. L. Zhou, A. Khosla, A. Lapedriza, A. Oliva, A. Torralba. Learning deep features for discriminative localization. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 2921–2929, 2016. DOI: https://doi.org/10.1109/CVPR.2016.319.
K. K. Singh, Y. J. Lee. Hide-and-seek: Forcing a network to be meticulous for weakly-supervised object and action localization. In Proceedings of IEEE International Conference on Computer Vision, Venice, Italy, pp. 3544–3553, 2017. DOI: https://doi.org/10.1109/ICCV.2017.381.
J. Choe, H. Shim. Attention-based dropout layer for weakly supervised object localization. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Long Beach, USA, pp. 2214–2223, 2019. DOI: https://doi.org/10.1109/CVPR.2019.00232.
J. J. Mai, M. Yang, W. F. Luo. Erasing integrated learning: A simple yet effective approach for weakly supervised object localization. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 8763–8772, 2020. DOI: https://doi.org/10.1109/CVPR42600.2020.00879.
H. L. Xue, C. Liu, F. Wan, J. B. Jiao, X. Y. Ji, Q. X. Ye. DANet: Divergent activation for weakly supervised object localization. In Proceedings of IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, pp. 6588–6597, 2019. DOI: https://doi.org/10.1109/ICCV.2019.00669.
X. L. Zhang, Y. C. Wei, Y. Yang. Inter-image communication for weakly supervised localization. In Proceedings of the 16th European Conference on Computer Vision, Springer, Glasgow, UK, pp. 271–287, 2020. DOI: https://doi.org/10.1007/978-3-030-58529-7_17.
C. L. Zhang, Y. H. Cao, J. X. Wu. Rethinking the route towards weakly supervised object localization. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 13457–13466, 2020. DOI: https://doi.org/10.1109/CVPR42600.2020.01347.
J. Wei, Q. Wang, Z. Li, S. Wang, S. K. Zhou, S. G. Cui. Shallow feature matters for weakly supervised object localization. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Nashville, USA, pp. 5989–5997, 2021. DOI: https://doi.org/10.1109/CVPR46437.2021.00593.
W. Z. Lu, X. Jia, W. C. Xie, L. L. Shen, Y. C. Zhou, J. M. Duan. Geometry constrained weakly supervised object localization. In Proceedings of the 16th European Conference on Computer Vision, Springer, Glasgow, UK, pp. 481–496, 2020. DOI: https://doi.org/10.1007/978-3-030-58574-7_29.
S. Yang, Y. Kim, Y. Kim, C. Kim. Combinational class activation maps for weakly supervised object localization. In Proceedings of IEEE Winter Conference on Applications of Computer Vision, Snowmass, USA, pp. 2930–2938, 2020. DOI: https://doi.org/10.1109/WACV45572.2020.9093566.
X. J. Pan, Y. G. Gao, Z. W. Lin, F. Tang, W. M. Dong, H. L. Yuan, F. Y. Huang, C. S. Xu. Unveiling the potential of structure preserving for weakly supervised object localization. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Nashville, USA, pp. 11642–11651, 2021. DOI: https://doi.org/10.1109/CVPR46437.2021.01147.
G. Y. Guo, J. W. Han, F. Wan, D. W. Zhang. Strengthen learning tolerance for weakly supervised object localization. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Nashville, USA, pp. 7399–7408, 2021. DOI: https://doi.org/10.1109/CVPR46437.2021.00732.
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. A. Ma, Z. H. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C. Berg, L. Fei-Fei. ImageNet large scale visual recognition challenge. International Journal of Computer Vision, vol.115, no. 3, pp. 211–252, 2015. DOI: https://doi.org/10.1007/s11263-015-0816-y.
C. Wah, S. Branson, P. Welinder, P. Perona, S. Belongie. The caltech-UCSD birds-200-2011 dataset, [Online], Available: https://authors.library.caltech.edu/27452/1/CUB_200_2011.pdf, 2011.
J. Choe, S. J. Oh, S. Lee, S. Chun, Z. Akata, H. Shim. Evaluating weakly supervised object localization methods right. In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, Seattle, USA, pp. 3130–3139, 2020. DOI: https://doi.org/10.1109/CVPR42600.2020.00320.
K. Simonyan, A. Zisserman. Very deep convolutional networks for large-scale image recognition, [Online], Available: https://arxiv.org/abs/1409.1556, 2014.
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna. Rethinking the inception architecture for computer vision. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 2818–2826, 2016. DOI: https://doi.org/10.1109/CVPR.2016.308.
K. M. He, X. Y. Zhang, S. Q. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770–778, 2016. DOI: https://doi.org/10.1109/CVPR.2016.90.
S. Yun, D. Han, S. Chun, S. J. Oh, Y. Yoo, J. Choe. CutMix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of IEEE/CVF International Conference on Computer Vision, IEEE, Seoul, Republic of Korea, pp. 6022–6031, 2019. DOI: https://doi.org/10.1109/ICCV.2019.00612.
W. Gao, F. Wan, X. J. Pan, Z. L. Peng, Q. Tian, Z. J. Han, B. L. Zhou, Q. X. Ye. TS-CAM: Token semantic coupled attention map for weakly supervised object localization. In Proceedings of IEEE/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, pp. 2866–2875, 2021. DOI: https://doi.org/10.1109/ICCV48922.2021.00288.
J. Kim, J. Choe, S. Yun, N. Kwak. Normalization matters in weakly supervised object localization. In Proceedings of IEEE/CVF International Conference on Computer Vision, IEEE, Montreal, Canada, pp. 3407–3416, 2021. DOI: https://doi.org/10.1109/ICCV48922.2021.00341.
Acknowledgements
This work was partly supported by National Natural Science Foundation of China (No. 62072394), Natural Science Foundation of Hebei Province, China (No. F2021203019) and Hebei Key Laboratory Project, China (No. 20225 0701010046).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declared that they have no conflicts of interest to this work.
Additional information
Colored figures are available in the online version at https://link.springer.com/journal/11633
Wenjun Hui received the B. Sc. degree in communication engineering from Yanshan University, China in 2019, and the M.Sc. degree in electronic and communication engineering from Yanshan University, China in 2022. She is currently a Ph. D. degree candidate in information and communication engineering at Beijing Jiaotong University, China.
Her research interests include weakly supervised object localization and segmentation.
Guanghua Gu received the B. Sc. degree in communication engineering and the M. Sc. degree in circuits and systems from Yanshan University, China in 2001 and 2004, respectively, and the Ph. D. degree in signal and information processing from Beijing Jiaotong University, China in 2013. He was a visiting scholar of University of South Carolina, USA from 2015 to 2016. He is currently a professor with Yanshan University, China.
His resarch interests include image classification, image recognition and image retrieval.
Bo Wang received the B. Sc. degree in electronic information engineering from Hebei University of Technology, China in 2021. He is currently a master student in information and communication engineering at Yanshan University, China.
His research interest is cross-model generation.
Rights and permissions
About this article
Cite this article
Hui, W., Gu, G. & Wang, B. Shallow Feature-driven Dual-edges Localization Network for Weakly Supervised Localization. Mach. Intell. Res. 20, 923–936 (2023). https://doi.org/10.1007/s11633-022-1368-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11633-022-1368-6