SQ-GAN: Semantic Image Communications Using Masked Vector Quantization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917002275192832 |
|---|---|
| author | Pezone, Francesco Barbarossa, Sergio Caire, Giuseppe |
| author_facet | Pezone, Francesco Barbarossa, Sergio Caire, Giuseppe |
| contents | This work introduces Semantically Masked Vector Quantized Generative Adversarial Network (SQ-GAN), a novel approach integrating semantically driven image coding and vector quantization to optimize image compression for semantic/task-oriented communications. The method only acts on source coding and is fully compliant with legacy systems. The semantics is extracted from the image computing its semantic segmentation map using off-the-shelf software. A new specifically developed semantic-conditioned adaptive mask module (SAMM) selectively encodes semantically relevant features of the image. The relevance of the different semantic classes is task-specific, and it is incorporated in the training phase by introducing appropriate weights in the loss function. SQ-GAN outperforms state-of-the-art image compression schemes such as JPEG2000, BPG, and deep-learning based methods across multiple metrics, including perceptual quality and semantic segmentation accuracy on the reconstructed image, at extremely low compression rates. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_09520 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SQ-GAN: Semantic Image Communications Using Masked Vector Quantization Pezone, Francesco Barbarossa, Sergio Caire, Giuseppe Computer Vision and Pattern Recognition Image and Video Processing This work introduces Semantically Masked Vector Quantized Generative Adversarial Network (SQ-GAN), a novel approach integrating semantically driven image coding and vector quantization to optimize image compression for semantic/task-oriented communications. The method only acts on source coding and is fully compliant with legacy systems. The semantics is extracted from the image computing its semantic segmentation map using off-the-shelf software. A new specifically developed semantic-conditioned adaptive mask module (SAMM) selectively encodes semantically relevant features of the image. The relevance of the different semantic classes is task-specific, and it is incorporated in the training phase by introducing appropriate weights in the loss function. SQ-GAN outperforms state-of-the-art image compression schemes such as JPEG2000, BPG, and deep-learning based methods across multiple metrics, including perceptual quality and semantic segmentation accuracy on the reconstructed image, at extremely low compression rates. |
| title | SQ-GAN: Semantic Image Communications Using Masked Vector Quantization |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2502.09520 |