Generative Semantic Communication via Alternating Dual-Domain Posterior Sampling

• URL: http://arxiv.org/abs/2604.16796v1
• Date: Sat, 18 Apr 2026 03:00:02 GMT
• Title: Generative Semantic Communication via Alternating Dual-Domain Posterior Sampling
• Abstract summary: Generative semantic communication (SemCom) harnesses pretrained priors to improve the perceptual quality of wireless image transmission.<n>Existing generative SemCom receivers rely on maximum a posteriori (MAP) estimation.<n>We propose alternating dual-domain posterior sampling (ADDPS), a diffusion-based SemCom receiver.
• Score: 3.860428650013287
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative semantic communication (SemCom) harnesses pretrained generative priors to improve the perceptual quality of wireless image transmission. Existing generative SemCom receivers, however, rely on maximum a posteriori (MAP) estimation, which fundamentally cannot preserve the data distribution and thus limits achievable perceptual quality. Moreover, current diffusion-based approaches using single-domain guidance face significant limitations: latent-domain guidance is sensitive to channel noise, while image-domain guidance inherits decoder bias. Simply combining both domains simultaneously yields an overconfident pseudo-posterior. In this paper, we formulate semantic decoding as a Bayesian inverse problem and prove that posterior sampling achieves optimal perceptual quality by preserving the data distribution. Building on this insight, we propose alternating dual-domain posterior sampling (ADDPS), a diffusion-based SemCom receiver that alternately enforces latent-domain and image-domain consistency during the sampling process. This alternating strategy decomposes joint posterior sampling into simpler subproblems, avoiding gradient conflicts while retaining the complementary strengths of both domains. Experiments on FFHQ demonstrate that the proposed ADDPS achieves superior perceptual quality compared with existing methods.

Related papers

• DDS-UDA: Dual-Domain Synergy for Unsupervised Domain Adaptation in Joint Segmentation of Optic Disc and Optic Cup [9.302794224184263]
  Convolutional neural networks (CNNs) have achieved exciting performance in joint segmentation of optic disc and optic cup on single-institution datasets.<n>However, their clinical translation is hindered by two major challenges: limited availability of large-scale, high-quality degradation caused by domain shift.<n>We present the Dual-Domain Synergy UDA (DDS-UDA), a novel UDA framework that mitigates cross-domain interference and intra-domain generalization.
  arXiv  Detail & Related papers  (2026-03-07T08:30:14Z)
• UPDA: Unsupervised Progressive Domain Adaptation for No-Reference Point Cloud Quality Assessment [15.162901714953643]
  We propose the first unsupervised progressive domain adaptation (UPDA) framework for NR-PCQA.<n>At the coarse-grained stage, a discrepancy-aware coarse-grained alignment method is designed to capture quality relationships between cross-domain samples.<n>At the fine-grained stage, a perception fusion fine-grained alignment approach with symmetric feature fusion is developed to identify domain-invariant features.
  arXiv  Detail & Related papers  (2026-02-12T14:02:05Z)
• Prototype-Based Semantic Consistency Alignment for Domain Adaptive Retrieval [30.96614100772607]
  Prototype-Based Semantic Consistency Alignment (PSCA) is a two-stage framework for effective domain adaptive retrieval.<n> PSCA establishes class-level semantic connections, maximizing inter-class separability while gathering intra-class samples.<n>In the second stage, domain-specific quantization functions process the reconstructed features under mutual approximation constraints, generating unified binary hash codes across domains.
  arXiv  Detail & Related papers  (2025-12-04T07:16:42Z)
• Beyond Negative Transfer: Disentangled Preference-Guided Diffusion for Cross-Domain Sequential Recommendation [13.331414627413674]
  DPG-Diff is a novel Disentangled Preference-Guided Diffusion Model.<n>It decomposes user preferences into domain-invariant and domain-specific components, which jointly guide the reverse diffusion process.<n>It consistently outperforms state-of-the-art baselines across multiple metrics.
  arXiv  Detail & Related papers  (2025-08-30T06:56:56Z)
• Amortized Posterior Sampling with Diffusion Prior Distillation [55.03585818289934]
  Amortized Posterior Sampling is a novel variational inference approach for efficient posterior sampling in inverse problems.<n>Our method trains a conditional flow model to minimize the divergence between the variational distribution and the posterior distribution implicitly defined by the diffusion model.<n>Unlike existing methods, our approach is unsupervised, requires no paired training data, and is applicable to both Euclidean and non-Euclidean domains.
  arXiv  Detail & Related papers  (2024-07-25T09:53:12Z)
• Unified Domain Adaptive Semantic Segmentation [105.05235403072021]
  Unsupervised Adaptive Domain Semantic (UDA-SS) aims to transfer the supervision from a labeled source domain to an unlabeled target domain.<n>We propose a Quad-directional Mixup (QuadMix) method, characterized by tackling distinct point attributes and feature inconsistencies.<n>Our method outperforms the state-of-the-art works by large margins on four challenging UDA-SS benchmarks.
  arXiv  Detail & Related papers  (2023-11-22T09:18:49Z)
• Cyclically Disentangled Feature Translation for Face Anti-spoofing [61.70377630461084]
  We propose a novel domain adaptation method called cyclically disentangled feature translation network (CDFTN) CDFTN generates pseudo-labeled samples that possess: 1) source domain-invariant liveness features and 2) target domain-specific content features, which are disentangled through domain adversarial training. A robust classifier is trained based on the synthetic pseudo-labeled images under the supervision of source domain labels.
  arXiv  Detail & Related papers  (2022-12-07T14:12:34Z)
• Joint Attention-Driven Domain Fusion and Noise-Tolerant Learning for Multi-Source Domain Adaptation [2.734665397040629]
  Multi-source Unsupervised Domain Adaptation transfers knowledge from multiple source domains with labeled data to an unlabeled target domain. The distribution discrepancy between different domains and the noisy pseudo-labels in the target domain both lead to performance bottlenecks. We propose an approach that integrates Attention-driven Domain fusion and Noise-Tolerant learning (ADNT) to address the two issues mentioned above.
  arXiv  Detail & Related papers  (2022-08-05T01:08:41Z)
• Balancing Discriminability and Transferability for Source-Free Domain Adaptation [55.143687986324935]
  Conventional domain adaptation (DA) techniques aim to improve domain transferability by learning domain-invariant representations. The requirement of simultaneous access to labeled source and unlabeled target renders them unsuitable for the challenging source-free DA setting. We derive novel insights to show that a mixup between original and corresponding translated generic samples enhances the discriminability-transferability trade-off.
  arXiv  Detail & Related papers  (2022-06-16T09:06:22Z)
• Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing [53.82826073959756]
  Face anti-spoofing approach based on domain generalization(DG) has drawn growing attention due to its robustness forunseen scenarios. We propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels. To overcome the limitation, we propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels.
  arXiv  Detail & Related papers  (2021-05-06T06:04:59Z)
• Bi-Directional Generation for Unsupervised Domain Adaptation [61.73001005378002]
  Unsupervised domain adaptation facilitates the unlabeled target domain relying on well-established source domain information. Conventional methods forcefully reducing the domain discrepancy in the latent space will result in the destruction of intrinsic data structure. We propose a Bi-Directional Generation domain adaptation model with consistent classifiers interpolating two intermediate domains to bridge source and target domains.
  arXiv  Detail & Related papers  (2020-02-12T09:45:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.