Deep image semantic communication model for 6G
Current semantic communication models still have some parts that can be improved in processing image data, including effective image semantic codec, efficient semantic model training, and accurate image semantic evaluation.Hence, a deep image semantic communication (DeepISC) model was proposed.The v...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2023-03-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023050/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841540084882472960 |
|---|---|
| author | Feibo JIANG Yubo PENG Li DONG |
| author_facet | Feibo JIANG Yubo PENG Li DONG |
| author_sort | Feibo JIANG |
| collection | DOAJ |
| description | Current semantic communication models still have some parts that can be improved in processing image data, including effective image semantic codec, efficient semantic model training, and accurate image semantic evaluation.Hence, a deep image semantic communication (DeepISC) model was proposed.The vision transformer-based autoencoder (ViTA) network was used to achieve high-quality image semantic encoding and decoding.Then, an autoencoder realized channel codec to ensure the transmission of semantics on the channel.Furthermore, the discriminator network (DSN) and ViTA’s dual network architecture were used to jointly train, thus improving the semantic accuracy of the reconstructed image.Finally, for different downstream vision tasks, different evaluation indicators of image semantics were presented.Simulation results show that compared with other schemes, DeepISC can more effectively restore the semantic features of the transmitted image, so that the reconstructed image can show the same or similar semantic results as the original image in various downstream tasks. |
| format | Article |
| id | doaj-art-f3b80d1bd59d4e0fa6987ecc0d57117c |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2023-03-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-f3b80d1bd59d4e0fa6987ecc0d57117c2025-01-14T06:23:25ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2023-03-014419820859387977Deep image semantic communication model for 6GFeibo JIANGYubo PENGLi DONGCurrent semantic communication models still have some parts that can be improved in processing image data, including effective image semantic codec, efficient semantic model training, and accurate image semantic evaluation.Hence, a deep image semantic communication (DeepISC) model was proposed.The vision transformer-based autoencoder (ViTA) network was used to achieve high-quality image semantic encoding and decoding.Then, an autoencoder realized channel codec to ensure the transmission of semantics on the channel.Furthermore, the discriminator network (DSN) and ViTA’s dual network architecture were used to jointly train, thus improving the semantic accuracy of the reconstructed image.Finally, for different downstream vision tasks, different evaluation indicators of image semantics were presented.Simulation results show that compared with other schemes, DeepISC can more effectively restore the semantic features of the transmitted image, so that the reconstructed image can show the same or similar semantic results as the original image in various downstream tasks.http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023050/artificial intelligence6Gsemantic communicationimage recognitionfeature extraction |
| spellingShingle | Feibo JIANG Yubo PENG Li DONG Deep image semantic communication model for 6G Tongxin xuebao artificial intelligence 6G semantic communication image recognition feature extraction |
| title | Deep image semantic communication model for 6G |
| title_full | Deep image semantic communication model for 6G |
| title_fullStr | Deep image semantic communication model for 6G |
| title_full_unstemmed | Deep image semantic communication model for 6G |
| title_short | Deep image semantic communication model for 6G |
| title_sort | deep image semantic communication model for 6g |
| topic | artificial intelligence 6G semantic communication image recognition feature extraction |
| url | http://www.joconline.com.cn/zh/article/doi/10.11959/j.issn.1000-436x.2023050/ |
| work_keys_str_mv | AT feibojiang deepimagesemanticcommunicationmodelfor6g AT yubopeng deepimagesemanticcommunicationmodelfor6g AT lidong deepimagesemanticcommunicationmodelfor6g |