cs.LGNov 19, 2026

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

Authors: Keryan Chelouche, Petr Dobias, Nistor Grozavu, Olivier Romain

Organizations: ETIS UMR 8051, CY Cergy Paris Université, ENSEA, CNRS, Cergy, France · Fondation Léonie Chaptal, Sarcelles, France · ETIS UMR 8051, CY Cergy Paris Universite, ENSEA, CNRS, F-95000 Cergy, France · Fondation Léonie Chaptal, F-95200 Sarcelles, France

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.

Figures & tables

Explore similar work

CardsList
  1. BayaHAR: Lightweight Bayesian Few-Shot User Adaptation for On-Device Personalized Human Activity Recognition

    Jun 3, 2026Maximilian Burzer, Till Riedel, Michael Beigl +1Human Activity RecognitionDomain Adaptation

  2. A Universal Raw-IQ Radar Encoder for Cross-Sensor Human Sensing

    Nov 3, 2026Jonas Leo Mueller, Dario Zanca, Sebastian Hoefler +5mmWave Radar SensingRepresentation Learning

  3. DinoRADE: Full Spectral Radar-Camera Fusion with Vision Foundation Model Features for Multi-class Object Detection in Adverse Weather

    Apr 9, 2026Christof Leitgeb, Thomas Puchleitner, Max Peter Ronecker +1Object DetectionAutonomous Driving Perception