Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_cv 93% Match Research Paper Computer Vision Researchers,Multimedia Engineers,Machine Learning Engineers,Communications Engineers 3 weeks ago

SQ-GAN: Semantic Image Communications Using Masked Vector Quantization

generative-ai › gans
📄 Abstract

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.

Key Contributions

SQ-GAN introduces a novel approach to image compression for semantic/task-oriented communications by integrating semantically driven image coding with vector quantization. It utilizes a semantic-conditioned adaptive mask module (SAMM) to selectively encode relevant features, outperforming existing methods in both perceptual quality and semantic accuracy.

Business Value

Enables more efficient transmission of images for AI-driven applications (e.g., medical diagnosis, autonomous driving) by prioritizing semantically relevant information, reducing bandwidth requirements and improving task performance.