翻訳待ち：Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation

AI サービスが一時的に利用できないため、復旧後に翻訳を補完します。

--> [Submitted on 2 Aug 2026] Title:Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation View a PDF of the paper titled Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation, by Nafis Fuad and 2 other authors View PDF Abstract:Urban flooding poses an escalating threat to transportation infrastructure, yet no operational system provides real-time, street-level flood-depth estimates at centimeter resolution. This paper presents three vision-language models fine-tuned for continuous flood-depth estimation from street-level imagery: FloodLlama-Dense, a fully fine-tuned QLoRA baseline, and FloodLlama-MI5 and FloodLlama-MI6, interpretability-guided sparse variants that fine-tune only the top five and six causally relevant cross-attention layers identified through mechanistic interpretability analysis, respectively. Training uses an approximately 610,000-image subset of a 2.81-million-image synthetic corpus generated in Unreal Engine 5. The dataset combines single-vehicle subsets with 5 cm depth increments and mixed-vehicle subsets with 1 cm depth increments, spanning seven vehicle types, four weather conditions, and flood depths from 0 to 40 cm. FloodLlama-Dense achieves an MAE of 0.40 cm, an RMSE of 1.97 cm, and an Acc@5cm of 97.59%. Mechanistic interpretability analysis combining linear probing, logit lens, centered kernel alignment (CKA), and cross-attention entropy reveals a two-stage adaptation pattern: layers L13-L22 restructure visual representations, while depth first becomes linearly decodable at layer L23. FloodLlama-MI5 and FloodLlama-MI6 leverage this insight by fine-tuning only five or six of the eight cross-attention layers, achieving an 86-88% reduction in trainable parameters (6.55-7.86 million versus 54.4 million) with minimal accuracy loss. On a real-world benchmark, FloodLlama-MI6 achieves 98.62% accuracy, compared with 86.61% for the published STURM-FloodDepth baseline. Comments: This Paper is accepted in International Conference on Machine Learning and Application (ICMLA) 2026 Subjects: Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) Cite as: arXiv:2608.07562 [cs.CV] (or arXiv:2608.07562v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2608.07562 arXiv-issued DOI via DataCite Submission history From: Nafis Fuad [view email] [v1] Sun, 2 Aug 2026 22:38:25 UTC (366 KB) Full-text links: Access Paper: View a PDF of the paper titled Mechanistic Interpretability-Guided Selective Fine-Tuning of Vision-Language Models for Centimeter-Level Flood Depth Estimation, by Nafis Fuad and 2 other authors View PDF view license Current browse context: cs.CV new | recent | 2026-08 Change to browse by: cs cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Loading... Data provided by: Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)