# Training-Free Decoding of SAM3 Semantic Responses for Cross-Domain Infrastructure Crack Segmentation

Source: [Training-Free Decoding of SAM3 Semantic Responses for Cross-Domain Infrastructure Crack Segmentation](<https://www.sota2.com/research/paper/6a57142232fb9373148786dd>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-08-01T05:00:05.813Z

Authors: Zhanping Song, Shipeng Liu, Liang Zhao, Dengfeng Chen

Published: 2026-07-14T03:01:12.000Z

## Abstract

Cross-domain infrastructure crack segmentation is challenged by variations in materials, imaging conditions, crack morphology, and background interference. Although text-promptable foundation models reduce the need for task-specific training, SAM3's native proposal interface may not fully expose the crack evidence already encoded by the frozen model. We identify and quantify an output-interface mismatch in which the internal language-conditioned response preserves ground-truth-aligned crack evidence that is absent from the native proposal output. Based on this finding, we propose \\textbf{S}emantic-\\textbf{E}dge \\textbf{R}esponse \\textbf{D}ecoding (\\textbf{SERD}), a training-free method that replaces proposal-based readout with direct response decoding. SERD normalizes the dense response, calibrates it using a fixed Sobel prior, and applies a single threshold to produce the crack mask. SAM3 remains frozen without any target-domain annotations. Using one source domain solely for threshold selection, SERD achieves an average Crack IoU of 58.00\\% on five unseen datasets, compared with 54.33\\% for native SAM3. Across six rotated source-domain settings, it obtains a mean target-domain IoU of 60.23\\% and a Boundary F1 of 67.18\\%, exceeding SAM3 by 3.27 and 2.70 percentage points, respectively. The results show that task-aligned internal-response decoding provides a simple and transferable solution for cross-domain infrastructure crack segmentation. \\textit{Code is available at: \\href{https://github.com/xauat-liushipeng/SERD}{GitHub}.}

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2607.12292>)

[PDF](<https://arxiv.org/pdf/2607.12292.pdf>)
