Task-Oriented Semantic Feature Transmission for Multi-Task Satellite Remote Sensing over Low-SNR Channels
Read the original on arXiv Machine Learning →The paper proposes a task-oriented semantic feature transmission framework for satellite remote sensing over low‑signal‑to‑noise ratio (SNR) channels. Instead of reconstructing images first, it directly transmits semantic features extracted by a multitask‑pretrained backbone, using a lightweight channel adaptation module to reduce bandwidth and a feature restorer to recover task‑relevant structure after channel corruption. Experiments on scene classification and object detection under additive white Gaussian noise show consistent improvements over reconstruction‑oriented joint source‑channel coding baselines, especially in the low‑SNR regime.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.