English

SQ-GAN: Semantic Image Communications Using Masked Vector Quantization

Computer Vision and Pattern Recognition 2025-10-13 v2 Image and Video Processing

Abstract

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.

Keywords

Cite

@article{arxiv.2502.09520,
  title  = {SQ-GAN: Semantic Image Communications Using Masked Vector Quantization},
  author = {Francesco Pezone and Sergio Barbarossa and Giuseppe Caire},
  journal= {arXiv preprint arXiv:2502.09520},
  year   = {2025}
}

Comments

arXiv admin note: substantial text overlap with arXiv:2502.01675

R2 v1 2026-06-28T21:43:27.561Z