Papers › LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for...

LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset

4 Mar 2025arXiv:2503.02910archive 2025-07-28

Wenqi Guo, Yiyang Du, Shan Du

Gas leakage poses a significant hazard that requires prevention. Traditionally, human inspection has been used for detection, a slow and labour-intensive process. Recent research has applied machine learning techniques to this problem, yet there remains a shortage of high-quality, publicly available datasets. This paper introduces a synthetic dataset featuring diverse backgrounds, interfering foreground objects, diverse leak locations, and precise segmentation ground truth. We propose a zero-shot method that combines background subtraction, zero-shot object detection, filtering, and segmentation to leverage this dataset. Experimental results indicate that our approach significantly outperforms baseline methods based solely on background subtraction and zero-shot object detection with segmentation, reaching an IoU of 69\% overall. We also present an analysis of various prompt configurations and threshold settings to provide deeper insights into the performance of our method. The code and dataset will be released after publication.

PaperPDFCode

Code

weathon/Lang-Gas officialmentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ClassificationObject DetectionSegmentationZero-Shot Object Detectionobject-detection

Datasets

Introduced by this paper, per the archive.

SimGas

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Classification SimGas LangGas Frame Level Accuracy 0.89 #1 of 1 Archive leaderboard report
Segmentation SimGas LangGas IoU 0.69 #1 of 1 Archive leaderboard report
Segmentation SimGas LangGas Precision 0.82 #1 of 1 Archive leaderboard report
Segmentation SimGas LangGas Recall 0.82 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections