Energy-Efficient On-Device Image Restoration: Benchmarking Compact GANs and Mixed-Precision Quantization for Embedded Vision

References

[1] [1] Yamamoto NV, Berg NO, Krause WM. A Hybrid CNN-Transformer Model: An Application to Data Augmentation. arXiv preprint arXiv:2171.72855. 2018. https://arxiv.org/abs/2171.72855 [Crossref]

[2] [2] Costa TK, Zielinski RS, Verduzco MS. Attention-Based Networks for Motion Prediction in IoT Networks. Scientific Reports. 2023;9(2):151-160. https://doi.org/10.6160/i558076.2017.4446 [Crossref]

[3] [3] Kaushik P, Jain M, Shah A. A Low Power Low Voltage CMOS Based Operational Transconductance Amplifier for Biomedical Application. 2018. https://ijsetr.com/uploads/136245IJSETR17012-283.pdf [Crossref]

[4] [4] Marchetti AJ, Haddad JT. Ensemble Deep Learning for Image Classification in Smart Manufacturing. IEEE Transactions on Medical Imaging. 2020;9(7):346-354. https://doi.org/10.9099/x108745.2023.1355 [Crossref]

[5] [5] Kaushik P, Jain M. Design of low power CMOS low pass filter for biomedical application. J Electr Eng Technol (IJEET). 2018;9(5).

[6] [6] Wang VS, Mbeki DR, Kallas PB. Transfer Learning for Semantic Segmentation in Biomedical Signal Processing. Journal of Machine Learning Research. 2022;58(9):259-293. doi: 10.1695/a687806.2019.6621.

[7] [7] Kaushik P, Jain M. A Low Power SRAM Cell for High Speed Applications Using 90nm Technology. Csjournals.Com. 10. https://www.csjournals.com/IJEE/PDF10-2/66.%20Puneet.pdf [Crossref]

[8] [8] Rossi IF, Tanaka OV. Generative Adversarial Networks for Image Super-Resolution in Autonomous Driving. arXiv preprint arXiv:2373.15322. 2024. https://arxiv.org/abs/2373.15322 [Crossref]

[9] [9] Kaushik P, Jain M. A Low Power SRAM Cell for High Speed Applications Using 90nm Technology. Csjournals.Com. 2018 Dec;10(2):6. https://www.csjournals.com/IJEE/PDF10-2/66.%20Puneet.pdf [Crossref]

[10] [10] Ivanov CI, Mahmood KC. A Comparative Study of Metric Learning for Feature Extraction. Artificial Intelligence in Medicine. 2015;57(11):69-86. https://doi.org/10.1602/n300570.2021.7192 [Crossref]

[11] [11] Kaushik P, Jain M, Jain A. A Pixel-Based Digital Medical Images Protection Using Genetic Algorithm. International Journal of Electronics and Communication Engineering. 2018;11(1):31-37. ISSN 0974-2166.

[12] [12] Ferreira SR, Okafor GK, Kobayashi PH, Belkin NK. Self-Supervised Representation Learning for Motion Prediction in Clinical Diagnostics. Expert Systems with Applications. 2015;15(5):48-76. doi: 10.7092/v882786.2019.1955.

[13] [13] Kaushik P, Jain M, Shah A. A Low Power Low Voltage CMOS Based Operational Transconductance Amplifier for Biomedical Application. 2018.

[14] [14] Marchetti HC, Wojcik TT, Dominguez AP, Kallas EJ. A Comparative Study of Vision Transformers for Medical Image Synthesis. Multimedia Tools and Applications. 2019. https://doi.org/10.9148/v670986.2021.4608 [Crossref]

[15] [15] Ivanov EA, Garofalo CG, Suzuki GF, Larsson DL. Recurrent Neural Networks for Data Augmentation in Biomedical Signal Processing. arXiv preprint arXiv:2052.43235. 2016. https://arxiv.org/abs/2052.43235 [Crossref]

[16] [16] Kaushik P, Jain M. A Low Power SRAM Cell for High Speed Applications Using 90nm Technology. Csjournals.Com. 2018 Dec;10(2):6. https://www.csjournals.com/IJEE/PDF10-2/66.%20Puneet.pdf [Crossref]

[17] [17] Duarte HO, Nguyen BL, Haddad PA, Hoffmann RM. A Comparative Study of Vision Transformers for Tumor Detection. Knowledge-Based Systems. 2022. https://doi.org/10.8031/n496263.2022.5852 [Crossref]

[18] [18] Vargas OH, Marchetti ON, Novak NO. Metric Learning: An Application to Motion Prediction. Scientific Reports. 2017;25(12):63-74. doi: 10.7826/p832501.2024.2620.

[19] [19] Jain M, Shah A. Machine Learning with Convolutional Neural Networks (CNNs) in Seismology for Earthquake Prediction. Iconic Research and Engineering Journals. 2022;5(8):389-398. https://www.irejournals.com/paper-details/1707057 [Crossref]

[20] [20] Serrano WF, Cho RT. Lightweight Convolutional Networks: An Application to Anomaly Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2021;28(10):53-66. https://doi.org/10.2964/y952249.2020.9236 [Crossref]

[21] [21] Jain M, Srihari A. Comparison of CAD detection of mammogram with SVM and CNN. IRE Journals. 2021;8(6):63-75. https://www.irejournals.com/formatedpaper/1706647.pdf [Crossref]

[22] [22] Andersson MA, Chowdhury OF, Halvorsen IA, Mercado KI. Bayesian Deep Learning: An Application to Signal Reconstruction. arXiv preprint arXiv:2175.60974. 2020. https://arxiv.org/abs/2175.60974 [Crossref]

[23] [23] Marchetti BB, Suzuki VR, Sokolov BT, Kallas MG. Graph Neural Networks for Anomaly Detection in Medical Imaging. Pattern Recognition. 2017;58(2):31-70. https://doi.org/10.8154/b912856.2021.6852 [Crossref]

[24] [24] Fedorov TE, Wagner IH, Oliveira KP, Sandberg AS. Generative Adversarial Networks for Semantic Segmentation in Edge Devices. Neural Computing and Applications. 2023;52(2):93-130. https://doi.org/10.5170/y705818.2016.2638 [Crossref]

[25] [25] Wojcik BE, Tanaka BF, Sandberg ME. Lightweight Convolutional Networks for Fraud Detection in Medical Imaging. Expert Systems with Applications. 2016;10(9):113-151. https://doi.org/10.9260/s830215.2019.2062 [Crossref]

[26] [26] Yamamoto WD, Saito BI, Halvorsen AE, Kallas AH. Diffusion-Based Generation: An Application to Lesion Segmentation. Knowledge-Based Systems. 2020;52(10):286-295. doi: 10.3804/h809084.2022.7920.

[27] [27] Kaushik P, Jain M. A Low Power SRAM Cell for High Speed Applications Using 90nm Technology. Csjournals.Com. 10. https://www.csjournals.com/IJEE/PDF10-2/66.%20Puneet.pdf [Crossref]

[28] [28] Villanueva KO, Larsson RW, Berg RR. Recurrent Neural Networks for Medical Image Synthesis in Medical Imaging. Multimedia Tools and Applications. 2019;25(1):154-185. https://doi.org/10.8658/o679730.2017.2010 [Crossref]

[29] [29] Wojcik GJ, Andersson RB, Ivanov BL, Rossi AV. Vision Transformers: An Application to Anomaly Detection. Multimedia Tools and Applications. 2022;31(1):138-161. https://doi.org/10.3438/d892334.2015.4013 [Crossref]

[30] [30] Kaushik P, Jain M, Jain A. A pixel-based digital medical images protection using genetic algorithm. Int J Electron Commun Eng. 2018;11:31-37.

[31] [31] Jain M, Shah A. Convolutional neural networks for real-time object detection with raspberry Pi. 2021. https://wjaets.com/sites/default/files/WJAETS-2021-0067.pdf. https://doi.org/10.30574/wjaets.2021.4.1.0067 [Crossref]

[32] [32] Mercado HK, Delgado AR, Kobayashi KP, Wojcik DO. A Comparative Study of Metric Learning for Tumor Detection. IEEE Transactions on Image Processing. 2015;31(12):23-57. https://doi.org/10.5804/i872420.2022.3792 [Crossref]

[33] [33] Jain M, Shah A. A multi-modal CNN framework for integrating medical imaging for COVID-19 Diagnosis. World Journal of Advanced Research and Reviews. 2020;8(3):475-493. https://doi.org/10.30574/wjarr.2020.8.3.0418 [Crossref]

[34] [34] Rossi LT, Cho LE. Capsule Networks for Feature Extraction in Surveillance Systems. Neural Computing and Applications. 2022. https://doi.org/10.5539/r484485.2018.9958 [Crossref]

[35] [35] Vargas TM, Halvorsen PG, Navarro CA. A Hybrid CNN-Transformer Model: An Application to Signal Reconstruction. IEEE Journal of Biomedical and Health Informatics. 2020;19(9):348-373. https://doi.org/10.6165/i923800.2019.8447 [Crossref]

[36] [36] Sandberg GO, Xu LN, Duarte FD, Quintero AF. Encoder-Decoder Networks: An Application to Anomaly Detection. Neural Computing and Applications. 2015. https://doi.org/10.2071/e142168.2022.3029 [Crossref]

[37] [37] Kaushik P. STUDY AND ANALYSIS OF IMAGE ENCRYPTION ALGORITHM BASED ON ARNOLD TRANSFORMATION. INTERNATIONAL JOURNAL of COMPUTER ENGINEERING and TECHNOLOGY (IJCET). 2018;9(5):59-63. https://iaeme.com/Home/article_id/IJCET_09_05_008 [Crossref]

[38] [38] Serrano WI, Jimenez JI, Kang RP. Vision Transformers for Lesion Segmentation in Healthcare Systems. arXiv preprint arXiv:2368.33978. 2015. https://arxiv.org/abs/2368.33978 [Crossref]

[39] [39] Kaushik P, Jain M. Design of low power CMOS low pass filter for biomedical application. International Journal of Electrical Engineering & Technology (IJEET). 2018;9(5).

[40] [40] Pappas DB, Zhang IO, Mahmood OJ. Deep Residual Learning: An Application to Disease Classification. Pattern Recognition. 2020;67(7):177-203. https://doi.org/10.4582/c969473.2018.6127 [Crossref]

[41] [41] Moreau OV, Andersson LI. Deep Residual Learning for Signal Reconstruction in Edge Devices. Expert Systems with Applications. 2024;51(6):113-125. https://doi.org/10.4956/h532610.2016.4966 [Crossref]

[42] [42] Schneider NV, Vasquez RO, Silva BI. Transfer Learning for Image Classification in Radiology. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2016. https://doi.org/10.8595/l248077.2021.9128 [Crossref]

[43] [43] Tanaka EV, Maddox WL, Navarro HI, Schneider HM. A Comparative Study of Encoder-Decoder Networks for Image Segmentation. arXiv preprint arXiv:2391.58539. 2020. https://arxiv.org/abs/2391.58539 [Crossref]

[44] [44] Jain M, Kaushik P, Shah A. Comparison of VGG16 and VGG19 Convolutional Neural Network (CNN) Layers on MRI Brain Tumor Detection. International Journal of Trend in Scientific Research and Development (IJTSRD). 2016 Dec;1(1):275-280. ISSN 2456-6470. https://www.ijtsrd.com/papers/ijtsrd3542.pdf [Crossref]

[45] [45] Radovanovic PP, Dominguez MR, Sokolov VO, Andersson FJ. Capsule Networks for Image Classification in Healthcare Systems. Medical Image Analysis. 2019;38(11):352-359. https://doi.org/10.7881/u431925.2022.8500 [Crossref]

[46] [46] Brandt LJ, Xu TV, Duarte VI. Diffusion-Based Generation: An Application to Disease Classification. IEEE Access. 2018. https://doi.org/10.2994/d642360.2022.8470 [Crossref]

@article{1722519,
      author = {Devang Kulkarni, Lena Havlik, Priyanka Menon},
      title = {Energy-Efficient On-Device Image Restoration: Benchmarking Compact GANs and Mixed-Precision Quantization for Embedded Vision},
      journal = {Iconic Research And Engineering Journals},
      year = {2022},
      volume = {6},
      number = {4},
      pages = {233-238},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722519.pdf},
      abstract = {On-device image restoration must remove noise and blur while respecting tight energy budgets. We benchmark three compact restoration GANs under mixed-precision quantization, where weights are held at INT8 and the most sensitive activations remain in FP16. Across denoising and deblurring benchmarks, the mixed-precision scheme recovers nearly full-precision fidelity while lowering per-frame energy to as little as 96 mJ, establishing a favourable accuracy-per-joule frontier for embedded vision.},
      month = {October},
      doi = {https://doi.org/10.64388/IREV6I4-1722519}
  }