Task-Oriented Semantic Feature Transmission for Multi-Task Satellite Remote Sensing over Low-SNR Channels
A task-oriented semantic transmission framework sends remote-sensing features instead of images, improving classification and detection over low-SNR satellite channels.
The paper proposes bypassing the reconstruct-then-infer paradigm in satellite remote sensing by directly transmitting semantic features extracted by a multitask-pretrained backbone. A lightweight channel adaptation module compresses feature dimensionality for bandwidth, and a feature restorer recovers task-relevant structure after channel corruption under random-SNR training. In AWGN settings, the approach consistently outperforms reconstruction-oriented JSCC baselines on scene classification and object detection, with the largest gains in the low-SNR regime.
- Transmits task-oriented semantic features instead of reconstructed images
- Channel adaptation module compresses features to reduce bandwidth
- Largest accuracy improvements occur in the low-SNR regime
Full article123 words · extracted from arxiv.org · click to collapse
Conventional satellite remote sensing transmission follows a reconstruct-then-infer paradigm that optimizes pixel-level fidelity, creating an objective mismatch with downstream tasks such as classification and detection, especially at low SNR. This paper investigates a task-oriented framework that bypasses image reconstruction and directly transmits semantic features extracted by a multitask-pretrained backbone. A lightweight channel adaptation module (CAM) compresses feature dimensionality for bandwidth reduction, and a feature restorer recovers task-relevant structure after channel corruption. With the backbone frozen, the CAM and task-specific downstream heads are jointly optimized with task and feature-level supervision under random-SNR training. Under the adopted AWGN setting, experiments on scene classification and object detection show consistent gains over reconstruction-oriented JSCC baselines across different SNR conditions, with the largest improvements in the low-SNR regime.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.20150