Back to the research

Published research / ACM SenSys 2025

Proteus

Learning with vision, sensing with radar.

Transferring visual knowledge to mmWave representations, with more informative radar imaging.

Proteus radar sensing prototype and plant target
The Proteus experimental setup, reproduced from the public paper.

A second modality can shape learning without becoming a permanent deployment requirement.

Proteus / 2025

The question

Can a radar recover useful wetness information without keeping a camera in the inference loop?

The idea

Reduce SAR speckle, incorporate phase-angle information, and train an mmWave student using an RGB teacher.

What the evidence shows

Experiments on commercial radar evaluate leaf wetness classification across environmental scenarios. An RGB teacher guides training; the student uses mmWave observations at inference. The evaluation concerns cross-modal learning for this sensing task.

Source: ACM SenSys 2025

What it opens up

The work highlights the importance of what the radar representation preserves. It motivates my broader question: which physical distinctions can an incomplete observation actually support?