cs.CVSep 28, 2025

Fieldable Low-Light Multi-Task Perception via Foundation-Model-Assisted Domain Adaptation

Authors: Beomseok Kang, Niluthpol Chowdhury Mithun, Mikhail Sizintsev, Han-Pang Chiu, Supun Samarasekera

Organizations: Beomseok Kang is with Seoul National University, Seoul, South Korea. · Niluthpol Chowdhury Mithun, Mikhail Sizintsev, Han-Pang Chiu, and Supun Samarasekera are with SRI International, Princeton, NJ, USA.

Abstract

Fieldable low-light perception systems require both semantic and geometric scene understanding under severe domain shift and embedded compute constraints. We present FAMDA, a foundation-model-assisted self-training framework for unsupervised domain adaptation (UDA) in multi-task dense prediction. The framework integrates segmentation and depth foundation models into a self-training paradigm to generate high-quality pseudo-labels for the target domain, distilling their generalization capabilities into a single lightweight student network. To connect the method to deployment, we instantiate the adapted student on a compact handheld low-light prototype with DomiNite imaging and Jetson Orin Nano embedded compute. We evaluate on standard synthetic-to-real multi-task UDA benchmarks for comparison with prior work and on our field-collected low-light dataset to validate daytime-to-low-light adaptation in the target application setting. Across these evaluations, the proposed approach achieves strong segmentation and depth accuracy with substantially lower memory use and inference latency than direct foundation-model inference, demonstrating a practical path toward embedded multi-task perception for low-light field systems.

Figures & tables

Explore similar work

CardsList
  1. Dual-Foundation Models for Unsupervised Domain Adaptation

    May 5, 2026Yerin Cheon, Aruna Balasubramanian, Francois RameauSynthetic-to-Real Domain AdaptationUnsupervised Domain Adaptation

  2. LFM: Leveraging Foundation Models for Source-Free Universal Domain Adaptation

    Jul 20, 2026Jing Li, Pan Liu, Meng Zhao +7Source-Free Domain AdaptationUnsupervised Domain Adaptation

  3. UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation

    Apr 12, 2026Haopeng Chen, Yihao Ai, Kabeen Kim +3Human Pose EstimationUnsupervised Domain Adaptation