Redução do Erro de Representação em Sensoriamento Compressivo com Modelos Generativos Usando Ajuste por Pivô

• João V. D. Sobrinho UFRJ
• Igor D. Alvarenga UFRJ
• Miguel Elias M. Campista UFRJ

DOI: https://doi.org/10.5753/sbrc.2023.516

Abstract

Reducing the transmitted data volume is essential for implementing networks with resource-limited and energy-constrained devices. In this sense, compressive sensing becomes a powerful alternative, as it moves the most com putationally complex task to the central server node, in contrast to the traditi onal compression scheme. Recently, a combination of compressive sensing and generative models appeared, giving rise to CSGM (Compressive Sensing using Generative Models). Although CSGM reduces the reconstruction error, it intro duces the so-called representation error. This paper proposes a technique based on model retraining in decompression time to reduce the representation error in CSGM. In this way, expanding the scope of the generative model to include the desired signal becomes possible. The results show performance gains in sig nal reconstruction of up to 30% compared with Deep Image Prior (DIP) and Wavelet Thresholding (WT) techniques, traditionally used in the literature.

References

Abbasian Dehkordi, S., Farajzadeh, K., Rezazadeh, J., Farahbakhsh, R., Sandrasegaran, K., and Abbasian Dehkordi, M. (2020). A survey on data aggregation techniques in iot sensor networks. Wireless Networks, 26(2):1243-1263.

Asim, M., Daniels, M., Leong, O., Ahmed, A., and Hand, P. (2020). Invertible generative models for inverse problems: mitigating representation error and dataset bias. In International Conference on Machine Learning, pages 399-409. PMLR.

Bora, A., Jalal, A., Price, E., and Dimakis, A. G. (2017). Compressed sensing using generative models. In International Conference on Machine Learning, pages 537-546. PMLR.

Candes, E., Romberg, J., and Tao, T. (2006). Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Transactions on Information Theory, 52(2):489-509.

Candes, E. J. (2008). The restricted isometry property and its implications for compressed sensing. Comptes rendus mathematique, 346(9-10):589-592.

Chen, S. and Donoho, D. (1994). Basis pursuit. In Proceedings of 1994 28th Asilomar Conference on Signals, Systems and Computers, volume 1, pages 41-44 vol.1.

Daras, G., Dean, J., Jalal, A., and Dimakis, A. G. (2021). Intermediate layer optimization for inverse problems using deep generative models.

Donoho, D. (2006). Compressed sensing. IEEE Transactions on Information Theory, 52(4):1289-1306.

Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial networks.

Karras, T., Aittala, M., Hellsten, J., Laine, S., Lehtinen, J., and Aila, T. (2020a). Training generative adversarial networks with limited data. In Proc. NeurIPS.

Karras, T., Laine, S., and Aila, T. (2018). A style-based generator architecture for generative adversarial networks.

Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., and Aila, T. (2020b). Analyzing and improving the image quality of stylegan. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 8107-8116.

Kaur, M. and Munjal, A. (2020). Data aggregation algorithms for wireless sensor network: a review. Ad Hoc Networks, 100:102083.

Ketshabetswe, K. L., Zungeru, A. M., Mtengi, B., Lebekwe, C. K., and Prabaharan, S. (2021). Data compression algorithms for wireless sensor networks: A review and comparison. IEEE Access, 9:136872-136891.

Nakas, C., Kandris, D., and Visvardis, G. (2020). Energy efficient routing in wireless sensor networks: a comprehensive survey. Algorithms, 13(3):72.

Roich, D., Mokady, R., Bermano, A. H., and Cohen-Or, D. (2022). Pivotal tuning for latent-based editing of real images. ACM Transactions on Graphics (TOG), 42(1):1-13.

Singh, J., Kaur, R., and Singh, D. (2021). Energy harvesting in wireless sensor networks: A taxonomic survey. International Journal of Energy Research, 45(1):118-140.

Ulyanov, D., Vedaldi, A., and Lempitsky, V. (2018). Deep image prior. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Wu, Y., Rosca, M., and Lillicrap, T. (2019). Deep compressed sensing. In Chaudhuri, K. and Salakhutdinov, R., editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 6850-6860. PMLR.

Xia, W., Zhang, Y., Yang, Y., Xue, J.-H., Zhou, B., and Yang, M.-H. (2022). Gan inversion: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence.

Zhang, R., Isola, P., Efros, A. A., Shechtman, E., and Wang, O. (2018). The unreasonable effectiveness of deep features as a perceptual metric. CoRR, abs/1801.03924.