Semantic Packet Aggregation and Repeated Transmission for Text-to-Image Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917972409319424 |
|---|---|
| author | Lee, Seunghun Park, Jihong Choi, Jinho Park, Hyuncheol |
| author_facet | Lee, Seunghun Park, Jihong Choi, Jinho Park, Hyuncheol |
| contents | Text-based communication is expected to be prevalent in 6G applications such as wireless AI-generated content (AIGC). Motivated by this, this paper addresses the challenges of transmitting text prompts over erasure channels for a text-to-image AIGC task by developing the semantic segmentation and repeated transmission (SMART) algorithm. SMART groups words in text prompts into packets, prioritizing the task-specific significance of semantics within these packets, and optimizes the number of repeated transmissions. Simulation results show that SMART achieves higher similarities in received texts and generated images compared to a character-level packetization baseline, while reducing computing latency by orders of magnitude compared to an exhaustive search baseline. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23734 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Semantic Packet Aggregation and Repeated Transmission for Text-to-Image Generation Lee, Seunghun Park, Jihong Choi, Jinho Park, Hyuncheol Signal Processing Text-based communication is expected to be prevalent in 6G applications such as wireless AI-generated content (AIGC). Motivated by this, this paper addresses the challenges of transmitting text prompts over erasure channels for a text-to-image AIGC task by developing the semantic segmentation and repeated transmission (SMART) algorithm. SMART groups words in text prompts into packets, prioritizing the task-specific significance of semantics within these packets, and optimizes the number of repeated transmissions. Simulation results show that SMART achieves higher similarities in received texts and generated images compared to a character-level packetization baseline, while reducing computing latency by orders of magnitude compared to an exhaustive search baseline. |
| title | Semantic Packet Aggregation and Repeated Transmission for Text-to-Image Generation |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2503.23734 |