analiza aiqbench
This paper applies parameter-efficient adaptation (QKV LoRA plus a lightweight residual adapter) to a frozen vision-language segmentation model for pavement cracks in low light, training about 1.3% of the parameters. Its reported gains rest on benchmarks against zero-shot and fine-tuned baselines, so the key questions for readers are how well the approach transfers beyond the Crack9k and Crack12k splits and whether the released code reproduces those results.
DROA-CLIPSeg: Prompt-Guided Thin Crack Segmentation in Low-Light Conditions
arXiv:2610.33635v1 Announce Type: cross Abstract: Pavement crack segmentation under low light is degraded by reduced contrast, shadows, headlight glare, joints, stains, and wet seams. Existing crack segmentation methods mostly assume good illumination. Low-light enhancement methods improve visual quality, but they do not explicitly preserve crack topology. To address these limitations, we formulate low-light crack segmentation as a degradation-aware, prompt-grounded structural defect segmentation problem and propose DROA-CLIPSeg, a parameter-efficient framework that adapts a frozen CLIPSeg vision language backbone using two lightweight modules. QKV Low-Rank Adaptation is injected into the Q/K/V projections of the vision and text encoders to improve crack-specific image text alignment without backbone fine-tuning. The proposed Domain Residual Orthogonal Adapter (DROA) decomposes intermediate features into a dominant crack-domain branch, which captures recurring low-light crack patterns, and an orthogonal residual branch, which preserves faint, thin, and fragmented evidence usually suppressed by noise, shadow, or over-smoothing. We also introduce CrackLingo-9K and CrackLingo-12K, text augmented versions of Crack9k and Crack12k with crack-aware prompts. Training only approximately 1.93 M parameters, corresponding to 1.3% of the full model, DROA-CLIPSeg outperforms 9 zero-shot and 4 fine-tuned vision language baselines on both splits, generalises zero-shot to MVTec AD across textures and defect morphologies, and is supported by extensive ablations. Our source code is publicly available at https://github.com/VShuklacode/DROA-CLIPSeg
Abstract:Pavement crack segmentation under low light is degraded by reduced contrast, shadows, headlight glare, joints, stains, and wet seams. Existing crack segmentation methods mostly assume good illumination. Low-light enhancement methods improve visual quality, but they do not explicitly preserve crack topology. To address these limitations, we formulate low-light crack segmentation as a degradation-aware, prompt-grounded structural defect segmentation problem and propose DROA-CLIPSeg, a parameter-efficient framework that adapts a frozen CLIPSeg vision language backbone using two lightweight modules. QKV Low-Rank Adaptation is injected into the Q/K/V projections of the vision and text encoders to improve crack-specific image text alignment without backbone fine-tuning. The proposed Domain Residual Orthogonal Adapter (DROA) decomposes intermediate features into a dominant crack-domain branch, which captures recurring low-light crack patterns, and an orthogonal residual branch, which preserves faint, thin, and fragmented evidence usually suppressed by noise, shadow, or over-smoothing. We also introduce CrackLingo-9K and CrackLingo-12K, text augmented versions of Crack9k and Crack12k with crack-aware prompts. Training only approximately 1.93 M parameters, corresponding to 1.3% of the full model, DROA-CLIPSeg outperforms 9 zero-shot and 4 fine-tuned vision language baselines on both splits, generalises zero-shot to MVTec AD across textures and defect morphologies, and is supported by extensive ablations. Our source code is publicly available at this https URL
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2610.33635 [cs.CV]
(or arXiv:2610.33635v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2610.33635 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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.
Text integral sub licența deschisă a publicației · 308 cuvinte