analiza aiqbench
This research advances semantic image communication by introducing a channel-adaptive region adjacency graph carrier that explicitly encodes spatial relations between scene segments. By combining graph simplification with belief propagation, the method achieves superior semantic consistency under noisy conditions while reducing payload size compared to traditional dense tensor layouts. The work represents a significant step in optimizing joint source-channel coding for efficient transmission of task-relevant visual structures.
Channel-Adaptive Region Adjacency Graph Carriers for Semantic Image Communication
arXiv:2609.14616v1 Announce Type: cross Abstract: Semantic image communication seeks to preserve task-relevant scene structure under limited channel resources, but carriers are often dense latent tensors or grid-aligned semantic layouts that do not explicitly encode region-level relations. This work introduces a segmentation-derived region adjacency graph (RAG) carrier, termed channel-adaptive RAG (CA-RAG), for joint source-channel coding-style image communication. Nodes store interpretable region attributes, edges preserve adjacency, channel-adaptive graph simplification (CGS) controls the node budget, and semantic belief propagation refines noisy graph embeddings before diffusion-based reconstruction. On Cityscapes, pre-channel RAG payloads are several times smaller than compressed class-index layouts in a 2,000-image study. Under additive white Gaussian noise at signal-to-noise ratios from 0 to 15 dB, CA-RAG reports higher semantic consistency than deep joint source-channel coding and a same-decoder layout baseline, with comparable perceptual quality. At 10 dB, the full-budget rate-sweep point reaches mean intersection over union (mIoU) = 0.329 at approximately 3.3 x 10^3 channel uses, while the default adaptive-CGS setting reports mIoU = 0.294 at approximately 2.6 x 10^3 channel uses.
Abstract:Semantic image communication seeks to preserve task-relevant scene structure under limited channel resources, but carriers are often dense latent tensors or grid-aligned semantic layouts that do not explicitly encode region-level relations. This work introduces a segmentation-derived region adjacency graph (RAG) carrier, termed channel-adaptive RAG (CA-RAG), for joint source-channel coding-style image communication. Nodes store interpretable region attributes, edges preserve adjacency, channel-adaptive graph simplification (CGS) controls the node budget, and semantic belief propagation refines noisy graph embeddings before diffusion-based reconstruction. On Cityscapes, pre-channel RAG payloads are several times smaller than compressed class-index layouts in a 2,000-image study. Under additive white Gaussian noise at signal-to-noise ratios from 0 to 15 dB, CA-RAG reports higher semantic consistency than deep joint source-channel coding and a same-decoder layout baseline, with comparable perceptual quality. At 10 dB, the full-budget rate-sweep point reaches mean intersection over union (mIoU) = 0.329 at approximately 3.3 x 10^3 channel uses, while the default adaptive-CGS setting reports mIoU = 0.294 at approximately 2.6 x 10^3 channel uses.
6 pages, 5 figures, 7 tables. Accepted for presentation at IEEE GLOBECOM 2026, Macau. This is the author's accepted version; the final published version will be available via IEEE Xplore
Signal Processing (eess.SP); Machine Learning (cs.LG)
arXiv:2609.14616 [eess.SP]
(or arXiv:2609.14616v1 [eess.SP] for this version)
https://doi.org/10.48550/arXiv.2609.14616 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 216 cuvinte
Subiecte conexe
MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA
arXiv · 17 iun. 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · 27 aug. 2026
Toward Federated Multimodal Graph Foundation Models: A Topology-Aware Multimodal Alignment Framework
arXiv · 20 iul. 2026
From PDFs to insights: Architecting an intelligent document processing pipeline with AWS generative AI services
AWS · 12 iun. 2026