考虑任务模型缺陷，重新定义机器感知编码的压缩极限。
Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding
- 从间接率失真理论出发，分析任务编码的理论边界。
- 实验证明现有方法距离理论极限仍有显著差距。
- 适合研究高效视觉通信与模型压缩的学者参考。
任务导向源编码（TOSC）已成为机器中心推理系统中高效视觉数据通信的新范式，需在资源受限下联合优化码率、延迟和任务性能。尽管近期工作提出了面向机器的率失真界，但这些结果通常依赖于强任务可识别性假设，并忽略了部署的任务模型影响。本文从间接率失真理论视角重新审视单任务TOSC的基本极限，揭示了现有率失真界在现实场景中的可实现条件与局限性。随后，提出考虑任务模型次优性和架构约束的模型感知率失真界。在标准分类基准上的实验表明，当前学习型TOSC方案仍远未达到这些新界限，凸显发射端复杂性是主要瓶颈。
原文摘要 · Abstract (English)
Task-Oriented Source Coding (TOSC) has emerged as a paradigm for efficient visual data communication in machine-centric inference systems, where bitrate, latency, and task performance must be jointly optimized under resource constraints. While recent works have proposed rate-distortion bounds for coding for machines, these results often rely on strong assumptions on task identifiability and neglect the impact of deployed task models. In this work, we revisit the fundamental limits of single-TOSC through the lens of indirect rate-distortion theory. We highlight the conditions under which existing rate-distortion bounds are achievable and show their limitations in realistic settings. We then introduce task model-aware rate-distortion bounds that account for task model suboptimality and architectural constraints. Experiments on standard classification benchmarks confirm that current learned TOSC schemes operate far from these limits, highlighting transmitter-side complexity as a key bottleneck.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。