Abstract
A popular strategy for designing a semantic segmentation model is to utilize a well-established pre-trained Deep Convolutional Neural Network (DCNN) as a feature extractor and replace the classification head with a decoder to generate segmented outputs. The advantage of this strategy is the ability to obtain a ready-made backbone with additional knowledge. However, there are several disadvantages, such as a lack of architectural knowledge, a significant semantic gap among the deep feature maps, and a lack of control over architectural changes to reduce memory overhead. To overcome these issues, we first study the complete architecture of EfficientNetV1 and EfficientNetV2, analyzing the architectural and performance gaps. Based on this analysis, we develop an efficient segmentation model called Effi-Seg by implementing several architectural changes to the backbone. This approach leads to better semantic segmentation results with improved efficiency. To enhance contextualization and achieve accurate object localization in the scene, we introduce a feature refinement module (FRM) and a semantic aggregation module (SAM) in the decoder. The complete segmentation network comprises only 1.49 million parameters and 8.4 GFLOPs. We evaluate the performance of the proposed model using three popular benchmarks, and it demonstrates highly competitive results on all three datasets while maintaining excellent efficiency.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abu Alhaija, H., Mustikovela, S.K., Mescheder, L., Geiger, A., Rother, C.: Augmented reality meets computer vision: efficient data generation for urban driving scenes. Int. J. Comput. Vis. 126(9), 961–972 (2018). https://doi.org/10.1007/s11263-018-1070-x
Cai, J., Liu, Y., Qin, P.: Attention based quick network with optical flow estimation for semantic segmentation. IEEE Access 11, 12402–12413 (2023)
Cai, W., Wang, B.: DSE-Net: deep semantic enhanced network for mobile tongue image segmentation. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds.) ICONIP 2022. CCIS, vol. 1794, pp. 138–150. Springer, Singapore (2023). https://doi.org/10.1007/978-981-99-1648-1_12
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 833–851. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01234-2_49
Choi, S., Kim, J.T., Choo, J.: Cars can’t fly up in the sky: improving urban-scene segmentation via height-driven attention networks. In: Proceedings of the CVPR, pp. 9373–9383 (2020)
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the CVPR (2016)
Du, J.: Understanding of object detection based on CNN family and YOLO. In: Journal of Physics: Conference Series, vol. 1004, p. 012029. IOP Publishing (2018)
Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the CVPR, pp. 580–587 (2014)
Gruosso, M., Capece, N., Erra, U.: Human segmentation in surveillance video with deep learning. Multimedia Tools Appl. 80, 1175–1199 (2021). https://doi.org/10.1007/s11042-020-09425-0
Howard, A., et al.: Searching for MobileNetV3. In: Proceedings of the ICCV, pp. 1314–1324 (2019)
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the CVPR, pp. 3431–3440 (2015)
Noh, H., Hong, S., Han, B.: Learning deconvolution network for semantic segmentation. In: Proceedings of the ICCV, pp. 1520–1528 (2015)
Ochs, M., Kretz, A., Mester, R.: SDNet: semantically guided depth estimation network. In: Fink, G.A., Frintrop, S., Jiang, X. (eds.) DAGM GCPR 2019. LNCS, vol. 11824, pp. 288–302. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-33676-9_20
Paszke, A., Chaurasia, A., Kim, S., Culurciello, E.: ENet: a deep neural network architecture for real-time semantic segmentation. arXiv preprint arXiv:1606.02147 (2016)
Progga, P.H., Shatabda, S.: iResSENet: an accurate convolutional neural network for retinal blood vessel segmentation. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds.) ICONIP 2022. LNCS, vol. 13625, pp. 567–578. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-30111-7_48
Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24574-4_28
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Singha, T., Bergemann, M., Pham, D.S., Krishna, A.: SCMNet: shared context mining network for real-time semantic segmentation. In: Proceedings of the DICTA, pp. 1–8. IEEE (2021)
Singha, T., Bergemann, M., Pham, D.S., Krishna, A.: SC-CrackSeg: a real-time shared feature pyramid network for crack detection and segmentation. In: Proceedings of the DICTA, pp. 1–8 (2022)
Singha, T., Pham, D.S., Krishna, A.: FANet: feature aggregation network for semantic segmentation. In: Proceedings of the DICTA, pp. 1–8. IEEE (2020)
Singha, T., Pham, D.S., Krishna, A.: A real-time semantic segmentation model using iteratively shared features in multiple sub-encoders. Pattern Recogn. 140, 109557 (2023)
Singha, T., Pham, D.-S., Krishna, A., Dunstan, J.: Efficient segmentation pyramid network. In: Yang, H., Pasupa, K., Leung, A.C.-S., Kwok, J.T., Chan, J.H., King, I. (eds.) ICONIP 2020. CCIS, vol. 1332, pp. 386–393. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-63820-7_44
Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the CVPR, pp. 7262–7272 (2021)
Tan, M., Le, Q.: EfficientNet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the ICML, pp. 6105–6114. PMLR (2019)
Tan, M., Le, Q.: EfficientNetV2: smaller models and faster training. In: Proceedings of the ICML, pp. 10096–10106. PMLR (2021)
Tan, M., Pang, R., Le, Q.V.: EfficientDet: scalable and efficient object detection. In: Proceedings of the CVPR, pp. 10781–10790 (2020)
Targ, S., Almeida, D., Lyman, K.: ResNet in ResNet: generalizing residual architectures. arXiv preprint arXiv:1603.08029 (2016)
Xiang, W., Mao, H., Athitsos, V.: ThunderNet: a turbo unified network for real-time semantic segmentation. In: Proceedings of the WACV, pp. 1789–1796. IEEE (2019)
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 334–349. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01261-8_20
Yu, F., et al.: BDD100K: a diverse driving dataset for heterogeneous multitask learning. In: Proceedings of the CVPR, pp. 2636–2645 (2020)
Zhang, W., et al.: TopFormer: token pyramid transformer for mobile semantic segmentation. In: Proceedings of the CVPR, pp. 12083–12093 (2022)
Zhao, H., Qi, X., Shen, X., Shi, J., Jia, J.: ICNet for real-time semantic segmentation on high-resolution images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11207, pp. 418–434. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01219-9_25
Zhao, H., Shi, J., Qi, X., Wang, X., Jia, J.: Pyramid scene parsing network. In: Proceedings of the CVPR, pp. 2881–2890 (2017)
Zhu, Y., et al.: Improving semantic segmentation via video propagation and label relaxation. In: Proceedings of the CVPR, pp. 8856–8865 (2019)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Singha, T., Pham, DS., Krishna, A. (2024). Effi-Seg: Rethinking EfficientNet Architecture for Real-Time Semantic Segmentation. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Lecture Notes in Computer Science, vol 14451. Springer, Singapore. https://doi.org/10.1007/978-981-99-8073-4_5
Download citation
DOI: https://doi.org/10.1007/978-981-99-8073-4_5
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8072-7
Online ISBN: 978-981-99-8073-4
eBook Packages: Computer ScienceComputer Science (R0)