Model-Aware Rate-Distortion Limits for Task-Oriented Source Coding
This work addresses the fundamental limits of efficient visual data communication for machine inference systems, though it is incremental in refining existing theoretical bounds.
The paper tackled the problem of defining rate-distortion limits for task-oriented source coding by accounting for task model suboptimality and constraints, showing that current learned schemes operate far from these new bounds.
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.