FLIM-based Salient Object Detection Networks with Adaptive Decoders
DOI:
https://doi.org/10.5753/jbcs.2026.5893Keywords:
Salient Object Detection, FLIM, Adaptive Decoders, DecodingAbstract
Salient Object Detection (SOD) methods can locate objects that stand out in an image, assign higher values to their pixels in a saliency map, and binarize the map outputting a predicted segmentation mask. A recent tendency is to investigate pre-trained lightweight models rather than deep neural networks in SOD tasks, coping with applications under limited computational resources. In this context, we have investigated lightweight networks using a methodology named Feature Learning from Image Markers (FLIM), which assumes that the encoder's kernels can be estimated from marker pixels on discriminative regions of a few representative images. This work proposes flyweight networks, hundreds of times lighter than lightweight models, for SOD by combining a FLIM encoder with an adaptive decoder, whose weights are estimated for each input image by a given heuristic function. Such FLIM networks are trained from three to four representative images only and without backpropagation, making the models suitable for applications under labeled data constraints as well. We study five adaptive decoders; two of them are introduced here. Differently from the previous ones that rely on one neuron per pixel with shared weights, the heuristic functions of the new adaptive decoders estimate the weights of each neuron per pixel. We compare FLIM models with adaptive decoders for two challenging SOD tasks with three lightweight networks from the state-of-the-art, two FLIM networks with decoders trained by backpropagation, and one FLIM network whose labeled markers define the decoder's weights. For one of the applications, we evaluate the generalization ability of the networks to six different datasets. The experiments demonstrate the advantages of the proposed networks over the baselines, revealing the importance of further investigating such methods in new applications.
Downloads
References
Achanta, R., Estrada, F., Wils, P., and Süsstrunk, S. (2008). Salient region detection and segmentation. In Computer Vision Systems: 6th International Conference, ICVS 2008 Santorini, Greece, May 12-15, 2008 Proceedings 6, pages 66-75. Springer. DOI: 10.1007/978-3-540-79547-6_7.
Bakas, S., Akbari, H., Sotiras, A., Bilello, M., Rozycki, M., Kirby, J. S., Freymann, J. B., Farahani, K., and Davatzikos, C. (2017). Advancing the cancer genome atlas glioma mri collections with expert segmentation labels and radiomic features. Scientific data, 4(1):1-13. DOI: 10.1038/sdata.2017.117.
Bakas, S., Reyes, M., Jakab, A., Bauer, S., Rempfler, M., Crimi, A., Shinohara, R. T., Berger, C., Ha, S. M., Rozycki, M., et al. (2018). Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the brats challenge. arXiv preprint arXiv:1811.02629. DOI: 10.17863/CAM.38755.
Borji, A., Cheng, M.-M., Hou, Q., Jiang, H., and Li, J. (2019). Salient object detection: A survey. Computational visual media, 5:117-150. DOI: 10.1007/s41095-019-0149-9.
Bragantini, J., Martins, S. B., Castelo-Fernandez, C., and Falcão, A. X. (2018). Graph-based image segmentation using dynamic trees. In Iberoamerican Congress on Pattern Recognition, pages 470-478. Springer. DOI: 10.1007/978-3-030-13469-3_55.
Cerqueira, M. A., Sprenger, F., Teixeira, B. C., and Falcão, A. X. (2023). Building brain tumor segmentation networks with user-assisted filter estimation and selection. In 18th International Symposium on Medical Information Processing and Analysis, volume 12567, pages 202-211. SPIE. DOI: 10.1117/12.2669770.
Cerqueira, M. A., Sprenger, F., Teixeira, B. C., and Falcão, A. X. (2024a). Interactive image selection and training for brain tumor segmentation network. In 2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pages 1-4. IEEE. DOI: 10.1109/EMBC53108.2024.10781962.
Cerqueira, M. A., Sprenger, F., Teixeira, B. C., Guimarães, S. J. F., and Falcão, A. X. (2024b). Interactive ground-truth-free image selection for flim segmentation encoders. In 2024 37th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 1-6. IEEE. DOI: 10.1109/SIBGRAPI62404.2024.10716300.
Chang, K.-Y., Liu, T.-L., Chen, H.-T., and Lai, S.-H. (2011). Fusing generic objectness and visual saliency for salient object detection. In 2011 International Conference on Computer Vision, pages 914-921. IEEE. DOI: 10.1109/ICCV.2011.6126333.
Chen, F., Li, S., Han, J., Ren, F., and Yang, Z. (2024). Review of lightweight deep convolutional neural networks. Archives of Computational Methods in Engineering, 31(4):1915-1937. DOI: 10.1007/s11831-023-10032-z.
Cheng, M.-M., Mitra, N. J., Huang, X., Torr, P. H., and Hu, S.-M. (2014). Global contrast based salient region detection. IEEE transactions on pattern analysis and machine intelligence, 37(3):569-582. DOI: 10.1109/TPAMI.2014.2345401.
De Souza, I. E., Benato, B. C., and Falcão, A. X. (2020). Feature learning from image markers for object delineation. In 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 116-123. IEEE. DOI: 10.1109/SIBGRAPI51738.2020.00024.
De Souza, I. E. and Falcão, A. X. (2020). Learning cnn filters from user-drawn image markers for coconut-tree image classification. IEEE Geoscience and Remote Sensing Letters, 19:1-5. DOI: 10.1109/LGRS.2020.3020098.
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., and Fei-Fei, L. (2009). Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248-255. IEEE. DOI: 10.1109/CVPR.2009.5206848.
Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., and Xu, C. (2020). Ghostnet: More features from cheap operations. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1580-1589. DOI: 10.1109/CVPR42600.2020.00165.
He, S., Lau, R. W., Liu, W., Huang, Z., and Yang, Q. (2015). Supercnn: A superpixelwise convolutional neural network for salient object detection. International journal of computer vision, 115:330-344. DOI: 10.1007/s11263-015-0822-0.
He, X., Zhao, K., and Chu, X. (2021). Automl: A survey of the state-of-the-art. Knowledge-based systems, 212:106622. DOI: 10.1016/j.knosys.2020.106622.
Itti, L., Koch, C., and Niebur, E. (2002). A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on pattern analysis and machine intelligence, 20(11):1254-1259. DOI: 10.1109/34.730558.
Jiang, P., Ling, H., Yu, J., and Peng, J. (2013). Salient region detection by ufo: Uniqueness, focusness and objectness. In Proceedings of the IEEE international conference on computer vision, pages 1976-1983. DOI: 10.1109/ICCV.2013.248.
Joao., L., Cerqueira., M., Benato., B., and Falcão., A. (2024). Understanding marker-based normalization for flim networks. pages 612-623. DOI: 10.5220/0012385900003660.
Joao, L. d. M., Santos, B. M. d., Guimaraes, S. J. F., Gomes, J. F., Kijak, E., Falcão, A. X., et al. (2023). A flyweight cnn with adaptive decoder for schistosoma mansoni egg detection. arXiv preprint arXiv:2306.14840. DOI: 10.48550/arXiv.2306.14840.
Lee, G., Tai, Y.-W., and Kim, J. (2016). Deep saliency with encoded low level distance map and high level features. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 660-668. DOI: 10.1109/CVPR.2016.78.
Li, G., Liu, Z., Zhang, X., and Lin, W. (2023). Lightweight salient object detection in optical remote-sensing images via semantic matching and edge alignment. IEEE Transactions on Geoscience and Remote Sensing, 61:1-11. DOI: 10.1109/TGRS.2023.3235717.
Li, W., Zhang, Y., Shi, W., and Coleman, S. (2022). A cam-guided parameter-free attention network for person re-identification. IEEE Signal Processing Letters, 29:1559-1563. DOI: 10.1109/LSP.2022.3186273.
Liang, B. and Luo, H. (2024). Meanet: An effective and lightweight solution for salient object detection in optical remote sensing images. Expert Systems with Applications, 238:121778. DOI: 10.1016/j.eswa.2023.121778.
Lin, Y., Sun, H., Liu, N., Bian, Y., Cen, J., and Zhou, H. (2022). A lightweight multi-scale context network for salient object detection in optical remote sensing images. In 2022 26th international conference on pattern recognition (ICPR), pages 238-244. IEEE. DOI: 10.1109/ICPR56361.2022.9956350.
Liu, N., Han, J., and Yang, M.-H. (2018). Picanet: Learning pixel-wise contextual attention for saliency detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3089-3098. DOI: 10.1109/CVPR.2018.00326.
Liu, Y., Zhang, X.-Y., Bian, J.-W., Zhang, L., and Cheng, M.-M. (2021). Samnet: Stereoscopically attentive multi-scale network for lightweight salient object detection. IEEE Transactions on Image Processing, 30:3804-3814. DOI: 10.1109/TIP.2021.3065239.
Menze, B. H., Jakab, A., Bauer, S., Kalpathy-Cramer, J., Farahani, K., Kirby, J., Burren, Y., Porz, N., Slotboom, J., Wiest, R., et al. (2014). The multimodal brain tumor image segmentation benchmark (brats). IEEE transactions on medical imaging, 34(10):1993-2024. DOI: 10.1109/TMI.2014.2377694.
Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O. R., and Jagersand, M. (2020). U2-net: Going deeper with nested u-structure for salient object detection. Pattern recognition, 106:107404. DOI: 10.1016/j.patcog.2020.107404.
Qin, X., Zhang, Z., Huang, C., Gao, C., Dehghan, M., and Jagersand, M. (2019). Basnet: Boundary-aware salient object detection. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 7479-7489. DOI: 10.1109/CVPR.2019.00766.
Salvagnini, F. C. R., Gomes, J. F., Santos, C. A., Guimarães, S. J. F., and Falcão, A. X. (2024). Improving flim-based salient object detection networks with cellular automata. In 2024 37th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 1-6. IEEE. DOI: 10.1109/SIBGRAPI62404.2024.10716266.
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2018). Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510-4520. DOI: 10.1109/CVPR.2018.00474.
Soares, G. J., Cerqueira, M. A., Guimaraes, S. J. F., Gomes, J. F., and Falcão, A. X. (2024). Adaptive decoders for flim-based salient object detection networks. In 2024 37th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pages 1-6. IEEE. DOI: 10.1109/SIBGRAPI62404.2024.10716333.
Ullah, I., Jian, M., Hussain, S., Guo, J., Yu, H., Wang, X., and Yin, Y. (2020). A brief survey of visual saliency detection. Multimedia Tools and Applications, 79:34605-34645. DOI: 10.1007/s11042-020-08849-y.
Wang, L., Lu, H., Ruan, X., and Yang, M.-H. (2015). Deep networks for saliency detection via local estimation and global search. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3183-3192. DOI: 10.1109/CVPR.2015.7298938.
Wang, Z., Zhang, Y., Liu, Y., Qin, C., Coleman, S. A., and Kerr, D. (2023a). Larnet: Towards lightweight, accurate and real-time salient object detection. IEEE Transactions on Multimedia, 26:5207-5222. DOI: 10.1109/TMM.2023.3330082.
Wang, Z., Zhang, Y., Liu, Y., Zhu, D., Coleman, S. A., and Kerr, D. (2023b). Elwnet: An extremely lightweight approach for real-time salient object detection. IEEE Transactions on Circuits and Systems for Video Technology, 33(11):6404-6417. DOI: 10.1109/TCSVT.2023.3269951.
Zhang, X., Zhou, X., Lin, M., and Sun, J. (2018). Shufflenet: An extremely efficient convolutional neural network for mobile devices. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6848-6856. DOI: 10.1109/CVPR.2018.00716.
Zhao, R., Ouyang, W., Li, H., and Wang, X. (2015). Saliency detection by multi-context deep learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1265-1274. DOI: 10.1109/CVPR.2015.7298731.
Zhou, X., Shen, K., and Liu, Z. (2024). Admnet: Attention-guided densely multi-scale network for lightweight salient object detection. IEEE Transactions on Multimedia. DOI: 10.1109/TMM.2024.3413529.
Zhu, W., Liang, S., Wei, Y., and Sun, J. (2014). Saliency optimization from robust background detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2814-2821. DOI: 10.1109/CVPR.2014.360.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Gilson Junior Soares, Matheus Abrantes Cerqueira, Jancarlo F. Gomes, Laurent Najman, Silvio Jamil F. Guimarães, Alexandre X. Falcão
This work is licensed under a Creative Commons Attribution 4.0 International License.
