# Few-Shot LoRA Adaptation of a Flow-Matching Foundation Model for Cross-Spectral Object Detection

arXiv: https://arxiv.org/abs/2601.04381 · HTML: https://mlsanity.com/paper/2601.04381/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Inverse problems and image restoration, one of 14 directions in Diffusion models.
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 7 Jan 2026.

## Placed in

- Diffusion models / [Inverse problems and image restoration](https://mlsanity.com/diffusion/inverse-problems-and-image-restoration/)

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Diffusion Models in Vision: A Survey](https://mlsanity.com/paper/2209.04747/) (2022)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Unsupervised Image-to-Image Translation Networks](https://mlsanity.com/paper/1703.00848/) (2017)
- [LLVIP: A Visible-infrared Paired Dataset for Low-light Vision](https://mlsanity.com/paper/2108.10831/) (2021)
- [PID: Physics-Informed Diffusion Model for Infrared Image Generation](https://mlsanity.com/paper/2407.09299/) (2024)

## Built on by (most cited first, 1 of 1)

- [RGB-to-IR image translation for infrared vehicle detection in unseen UAV domains](https://mlsanity.com/paper/2609.02556/) (2026)

## Abstract (arXiv)

Foundation models for vision are predominantly trained on RGB data, while many safety-critical applications rely on non-visible modalities such as infrared (IR) and synthetic aperture radar (SAR). We study whether a single flow-matching foundation model pre-trained primarily on RGB images can be repurposed as a cross-spectral translator using only a few co-measured examples, and whether the resulting synthetic data can enhance downstream detection. Starting from FLUX.1 Kontext, we insert low-rank adaptation (LoRA) modules and fine-tune them on just 100 paired images per domain for two settings: RGB to IR on the KAIST dataset and RGB to SAR on the M4-SAR dataset. The adapted model translates RGB images into pixel-aligned IR/SAR, enabling us to reuse existing bounding boxes and train object detection models purely in the target modality. Across a grid of LoRA hyperparameters, we find that LPIPS computed on only 50 held-out pairs is a strong proxy for downstream performance: lower LPIPS consistently predicts higher mAP for YOLOv11n on both IR and SAR, and for DETR on KAIST IR test data. Using the best LPIPS-selected LoRA adapter, synthetic IR from external RGB datasets (LLVIP, FLIR ADAS) improves KAIST IR pedestrian detection, and synthetic SAR significantly boosts infrastructure detection on M4-SAR when combined with limited real SAR. Our results suggest that few-shot LoRA adaptation of flow-matching foundation models is a promising path toward foundation-style support for non-visible modalities.