Measurement Plasticity: Sensor-Level Adaptation for Vision–Language Models

Boyeong Im, Wooseok Lee, Yoojin Kwon, Hyung-Sin Kim

Keywords: Test-Time Adaptation, Vision–Language Models, Sensor-Level Adaptation, Physical Multi-View Learning

Abstract: We propose Multi-View Physical-prompt (MVP) for Test-Time Adaptation (TTA), a forward-only framework that moves TTA from tokens to photons by treating the camera exposure triangle (i.e., ISO, shutter speed, and aperture) as physical prompts. At inference, MVP acquires selected multiple physical views using a source-affinity score, evaluates digitally augmented variants of each retained view and filters the lowest-entropy predictions, and aggregates predictions with hard voting. This selection-then-vote design is simple, calibration-friendly, and requires no gradients or model modifications. On ImageNet-ES and ImageNet-ES-Diverse, MVP outperforms digital-only TTA on both Auto-Exposure and a combination with conventional sensor control. MVP remains effective under reduced parameter candidates that lower capture latency, demonstrating its practicality.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 13