Toward Sustainable Edge AI: Quantization-Aware Lightweight GANs for Power-Constrained Image Enhancement

References

[1] [1] Escobar DG, Vargas TI, Vasquez FO, Fischer AN. Encoder-Decoder Networks for Pose Estimation in IoT Networks. IEEE Access. 2016;66(12):162-175. https://doi.org/10.7907/z778324.2019.9789 [Crossref]

[2] [2] Berg IK, Ferreira WM, Navarro EE, Zielinski RC. Knowledge Distillation: An Application to Medical Image Synthesis. arXiv preprint arXiv:2120.36443. 2021. https://arxiv.org/abs/2120.36443 [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] Maddox RS, Ferreira NL, Grigoriev MA. Generative Adversarial Networks for Object Detection in Surveillance Systems. Computer Methods and Programs in Biomedicine. 2021;58(5):37-55. https://doi.org/10.5553/m989756.2021.7723 [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] Takahashi WC, Krause KG, Bianchi LD, Okafor VP. Ensemble Deep Learning for Image Super-Resolution in IoT Networks. IEEE Access. 2024. https://doi.org/10.2749/n188254.2021.5861 [Crossref]

[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] Wagner IL, Mbeki AE, Larsson OW, Thakur PK. U-Shaped Convolutional Networks for Object Detection in Autonomous Driving. IEEE Transactions on Image Processing. 2024. https://doi.org/10.9233/x892887.2022.1979 [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] Ibrahim ON, Nakamura AS, Belkin SL. Multi-Scale Feature Fusion for Image Classification in Clinical Diagnostics. Journal of Machine Learning Research. 2015;41(12):60-71. https://doi.org/10.8735/a898796.2021.4746 [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] Oliveira AH, Karlsson RT, Hoffmann OE, Novak FC. Metric Learning for Semantic Segmentation in Precision Agriculture. Computers in Biology and Medicine. 2022. https://doi.org/10.8403/f456864.2018.1909 [Crossref]

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

[14] [14] Larsson GP, Fedorov AD, Garofalo PE, Volkov JW. A Comparative Study of Knowledge Distillation for Object Detection. Neural Computing and Applications. 2019;43(11):147-179. https://doi.org/10.3847/q889918.2024.5931 [Crossref]

[15] [15] Yilmaz HV, Ortega HW, Maddox KD, Haddad MN. Multi-Scale Feature Fusion for Lesion Segmentation in Financial Systems. Knowledge-Based Systems. 2020. https://doi.org/10.3174/t165597.2021.5769 [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] Salcedo MR, Grigoriev ON, Mbeki IH. A Comparative Study of Contrastive Representation Learning for Disease Classification. IEEE Access. 2024. https://doi.org/10.7326/z445648.2021.6651 [Crossref]

[18] [18] Maddox NP, Sokolov IF, Novak OB. Federated Learning: An Application to Image Segmentation. Expert Systems with Applications. 2016;55(1):118-128. doi: 10.7476/b961109.2022.3385.

[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] Yilmaz IE, Bakshi VK, Tanaka HD, Cardoso OG. A Comparative Study of Attention-Based Networks for Lesion Segmentation. Medical Image Analysis. 2022;58(4):370-386. https://doi.org/10.5573/e507540.2016.7153 [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] Bianchi GP, Kowalski HE, Novak DT. A Comparative Study of Generative Adversarial Networks for Scene Understanding. Artificial Intelligence in Medicine. 2019;57(8):155-167. https://doi.org/10.6481/w101365.2021.5464 [Crossref]

[23] [23] Rossi FM, Delgado LC, Jimenez VO, Villanueva OW. Self-Supervised Representation Learning for Motion Prediction in Healthcare Systems. Information Sciences. 2022. https://doi.org/10.3761/t934792.2018.4243 [Crossref]

[24] [24] Wang IP, Nascimento OW, Kang DM. Knowledge Distillation: An Application to Fraud Detection. Artificial Intelligence in Medicine. 2023. https://doi.org/10.9226/b848774.2024.9007 [Crossref]

[25] [25] Krause OD, Jimenez WN. U-Shaped Convolutional Networks for Intrusion Detection in Smart Manufacturing. IEEE Transactions on Neural Networks and Learning Systems. 2018;65(12):250-258. doi: 10.6977/f636178.2015.9280.

[26] [26] Verduzco HF, Fischer NB, Krause LK, Ferreira NT. Self-Supervised Representation Learning for Semantic Segmentation in Clinical Diagnostics. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;56(8):121-157. https://doi.org/10.8042/p364060.2023.5224 [Crossref]

[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] Feng KM, Wojcik PM. A Comparative Study of Knowledge Distillation for Signal Reconstruction. IEEE Transactions on Neural Networks and Learning Systems. 2016;3(7):378-401. https://doi.org/10.8943/w744153.2017.3164 [Crossref]

[29] [29] Nascimento LV, Marchetti LA, Novak KK. Lightweight Convolutional Networks for Image Segmentation in Medical Imaging. IEEE Journal of Biomedical and Health Informatics. 2018;14(6):146-160. doi: 10.6184/q167245.2016.4504.

[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] Andersson KJ, Haddad JT, Quintero VN. Generative Adversarial Networks for Intrusion Detection in IoT Networks. Journal of Machine Learning Research. 2023;10(1):180-218. https://doi.org/10.1524/s877672.2021.2442 [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] Wang VB, Yamamoto HE. A Comparative Study of Metric Learning for Semantic Segmentation. IEEE Transactions on Medical Imaging. 2018;11(4):329-339. https://doi.org/10.6637/r952166.2020.8175 [Crossref]

[35] [35] Nascimento KO, Ferreira IR, Ibrahim NO. U-Shaped Convolutional Networks for Signal Reconstruction in Autonomous Driving. Knowledge-Based Systems. 2020;3(5):326-363. doi: 10.6719/p904327.2021.3043.

[36] [36] Yamamoto CF, Vasquez MC, Fischer KB. Capsule Networks: An Application to Semantic Segmentation. Pattern Recognition. 2020;10(7):188-207. https://doi.org/10.3615/h454161.2019.5393 [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] Okafor HN, Khedkar FE, Brandt BN, Oliveira VA. Knowledge Distillation for Intrusion Detection in Medical Imaging. Neural Networks. 2018;5(9):35-66. doi: 10.6944/o813035.2016.1948.

[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] Serrano CA, Ferreira CO, Jimenez MB, Haddad MF. Lightweight Convolutional Networks for Tumor Detection in Cybersecurity. Pattern Recognition. 2018;42(5):131-160. https://doi.org/10.4570/j319216.2024.7165 [Crossref]

[41] [41] Kowalski HK, Saito KT. A Comparative Study of Contrastive Representation Learning for Feature Extraction. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2022. https://doi.org/10.3837/w664535.2024.2666 [Crossref]

[42] [42] Nakamura VB, Khedkar BH, Rossi NA, Fischer TP. Bayesian Deep Learning: An Application to Medical Image Synthesis. IEEE Transactions on Medical Imaging. 2020;47(12):397-413. https://doi.org/10.4300/m630423.2021.4637 [Crossref]

[43] [43] Nakamura HO, Moreau ID. Lightweight Convolutional Networks for Intrusion Detection in Edge Devices. IEEE Journal of Biomedical and Health Informatics. 2017;36(4):195-211. https://doi.org/10.3088/k108622.2021.2631 [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] Rasmussen IA, Lindberg NV, Wojcik FC, Maddox VA. Graph Neural Networks for Image Classification in Neuroimaging. Applied Soft Computing. 2016;60(5):242-253. doi: 10.1634/e989289.2021.5421.

[46] [46] Maddox MO, Xu AO. A Hybrid CNN-Transformer Model for Semantic Segmentation in Edge Devices. Neural Computing and Applications. 2021;25(8):22-57. doi: 10.5061/b989291.2020.7887.

@article{1722520,
      author = {Mariana Cruz, Yusuf Demir, Anaya Reddy},
      title = {Toward Sustainable Edge AI: Quantization-Aware Lightweight GANs for Power-Constrained Image Enhancement},
      journal = {Iconic Research And Engineering Journals},
      year = {2022},
      volume = {6},
      number = {5},
      pages = {327-332},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1722520.pdf},
      abstract = {Sustainability is becoming a first-class metric for always-on vision systems. This paper takes an energy-first view of low-light image enhancement, using quantization-aware training (QAT) so that INT8 generators are optimized for accuracy under quantization from the outset. Beyond latency and fidelity, we report energy per frame and an estimated carbon cost, showing that QAT-tuned lightweight GANs cut the operational footprint of continuous enhancement by more than half without perceptible quality loss.},
      month = {November},
      doi = {https://doi.org/10.64388/IREV6I5-1722520}
  }