End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models
Edge computing-based image recognition applications face significant challenges, including increased latency and network load when transmitting large volumes of images to edge servers. To address these issues, this study proposes a novel solution that involves sending compressed data from a front-en...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10974964/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849324241548214272 |
|---|---|
| author | Ren Shibata Yuji Yamauchi |
| author_facet | Ren Shibata Yuji Yamauchi |
| author_sort | Ren Shibata |
| collection | DOAJ |
| description | Edge computing-based image recognition applications face significant challenges, including increased latency and network load when transmitting large volumes of images to edge servers. To address these issues, this study proposes a novel solution that involves sending compressed data from a front-end device over a network and subsequently reconstructing the images on the server side for recognition purposes. The proposed framework places the image recognition model directly after the image reconstruction model. The reconstruction model is based on a recurrent neural network, and ResNet-18 is used for recognition. This reduction in image quality results in lower recognition performance when using reconstructed images compared with original images. To mitigate this issue, we propose an end-to-end learning framework that jointly optimizes image reconstruction and recognition, specifically optimizing the reconstruction model for the recognition task. The proposed method achieves approximately 99% data compression without degrading classification performance. It improves image quality by 2.1 dB and classification accuracy by 11.2% over the baseline. The proposed method not only significantly improves the quality of reconstructed images without any loss in the image compression rate but also enhances the classification accuracy of these images. |
| format | Article |
| id | doaj-art-c8fede15974f431b9f635a4c94b4f88d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-c8fede15974f431b9f635a4c94b4f88d2025-08-20T03:48:46ZengIEEEIEEE Access2169-35362025-01-0113733557336110.1109/ACCESS.2025.356347610974964End-to-End Learning Framework Incorporating Image Reconstruction and Recognition ModelsRen Shibata0https://orcid.org/0009-0008-7490-8982Yuji Yamauchi1https://orcid.org/0009-0005-1560-4856Department of Robotics, Chubu University, Kasugai-shi, Aichi, JapanDepartment of Artificial Intelligence and Robotics, Chubu University, Kasugai, Aichi, JapanEdge computing-based image recognition applications face significant challenges, including increased latency and network load when transmitting large volumes of images to edge servers. To address these issues, this study proposes a novel solution that involves sending compressed data from a front-end device over a network and subsequently reconstructing the images on the server side for recognition purposes. The proposed framework places the image recognition model directly after the image reconstruction model. The reconstruction model is based on a recurrent neural network, and ResNet-18 is used for recognition. This reduction in image quality results in lower recognition performance when using reconstructed images compared with original images. To mitigate this issue, we propose an end-to-end learning framework that jointly optimizes image reconstruction and recognition, specifically optimizing the reconstruction model for the recognition task. The proposed method achieves approximately 99% data compression without degrading classification performance. It improves image quality by 2.1 dB and classification accuracy by 11.2% over the baseline. The proposed method not only significantly improves the quality of reconstructed images without any loss in the image compression rate but also enhances the classification accuracy of these images.https://ieeexplore.ieee.org/document/10974964/Edge computingend-to-end learningimage compressionimage recognition |
| spellingShingle | Ren Shibata Yuji Yamauchi End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models IEEE Access Edge computing end-to-end learning image compression image recognition |
| title | End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models |
| title_full | End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models |
| title_fullStr | End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models |
| title_full_unstemmed | End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models |
| title_short | End-to-End Learning Framework Incorporating Image Reconstruction and Recognition Models |
| title_sort | end to end learning framework incorporating image reconstruction and recognition models |
| topic | Edge computing end-to-end learning image compression image recognition |
| url | https://ieeexplore.ieee.org/document/10974964/ |
| work_keys_str_mv | AT renshibata endtoendlearningframeworkincorporatingimagereconstructionandrecognitionmodels AT yujiyamauchi endtoendlearningframeworkincorporatingimagereconstructionandrecognitionmodels |