SyncAI.news, a Varaisys broadcasting
Parameter-Efficient Adaptation of Self-supervised Vision Backbones Survives Distribution Shift in Radar Micro-Doppler HAR
KC

Keryan Chelouche (ETIS UMR 8051, CY Cergy Paris Universit\'e, ENSEA, CNRS, Cergy, France, Fondation L\'eonie Chaptal, Sarcelles, France), Petr Dobias (ETIS UMR 8051, CY Cergy Paris Universit\'e, ENSEA, CNRS, Cergy, France), Nistor Grozavu (ETIS UMR 8051, CY Cergy Paris Universit\'e, ENSEA, CNRS, Cergy, France), Olivier Romain (ETIS UMR 8051, CY Cergy Paris Universit\'e, ENSEA, CNRS, Cergy, France)

· 1 min read

ResearcharXiv cs.LG

Parameter-Efficient Adaptation of Self-supervised Vision Backbones Survives Distribution Shift in Radar Micro-Doppler HAR

arXiv:2611.25874v1 Announce Type: new Abstract: Micro-Doppler radar enables contactless, privacy-preserving human activity recognition (HAR), but deployment robustness remains underexplored. We compared full fine-tuning, frozen probing, and parameter-efficient fine-tuning (PEFT) using subject-disjoint in-distribution cross-validation and few-shot cross-age, cross-orientation, and cross-dataset transfer. Full fine-tuning suffered negative cross-dataset transfer, while frozen features under-adapted on cross-orientation. Only PEFT avoided both failures. We paired DINOv3 with all-layer principal-singular-direction adaptation (PiSSA), to our knowledge the first application of a self-supervised image foundation backbone to radar micro-Doppler HAR. DINOv3-PiSSA ranked first among PEFT methods in every evaluated setting. Under our protocol, its Small variant matched the in-distribution accuracy of the prior Base-size PEFT state of the art using 4.5x fewer total parameters, with only 3% trainable. It surpassed a size-matched variant of that baseline in every evaluated setting, with transfer gains increasing with shift severity: 2.1, 6.6, and 8.9 percentage points, respectively. Ablations attributed improvements to both pretraining and adapter recipe, with the pretraining contributing most under compound shift. Code and protocol are available at https://github.com/KeryanChelouche/udoppler-ssl.

Original source

This story was published by arXiv cs.LG and written by Keryan Chelouche (ETIS UMR 8051, CY Cergy Paris Universit\'e, ENSEA, CNRS, Cergy, France, Fondation L\'eonie Chaptal, Sarcelles, France), Petr Dobias (ETIS UMR 8051, CY Cergy Paris Universit\'e, ENSEA, CNRS, Cergy, France), Nistor Grozavu (ETIS UMR 8051, CY Cergy Paris Universit\'e, ENSEA, CNRS, Cergy, France), Olivier Romain (ETIS UMR 8051, CY Cergy Paris Universit\'e, ENSEA, CNRS, Cergy, France). SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News