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

arXiv: https://arxiv.org/abs/2503.02910 · HTML: https://mlsanity.com/paper/2503.02910/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 60 references that are in the map.
- First posted on arXiv 4 Mar 2025.

## Builds on (most cited first, 30 of 30)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [LISA: Reasoning Segmentation via Large Language Model](https://mlsanity.com/paper/2308.00692/) (2023)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks](https://mlsanity.com/paper/2311.06242/) (2023)
- [Simple Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2205.06230/) (2022)
- [One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos](https://mlsanity.com/paper/2409.19603/) (2024)
- [LLM-Seg: Bridging Image Segmentation and Large Language Model Reasoning](https://mlsanity.com/paper/2404.08767/) (2024)
- [Learning Multi-scale Features for Foreground Segmentation](https://mlsanity.com/paper/1808.01477/) (2018)
- [Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations](https://mlsanity.com/paper/2206.15462/) (2022)
- [BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen Videos](https://mlsanity.com/paper/1907.11371/) (2019)
- [Improved Visual Grounding through Self-Consistent Explanations](https://mlsanity.com/paper/2312.04554/) (2023)
- [Foreground Segmentation Using a Triplet Convolutional Neural Network for Multiscale Feature Encoding](https://mlsanity.com/paper/1801.02225/) (2018)
- [BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtraction](https://mlsanity.com/paper/2101.09585/) (2021)
- [Universal Background Subtraction based on Arithmetic Distribution Neural Network](https://mlsanity.com/paper/2104.08390/) (2021)
- [ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection](https://mlsanity.com/paper/2303.14679/) (2023)
- [Machine Vision for Natural Gas Methane Emissions Detection Using an Infrared Camera](https://mlsanity.com/paper/1904.08500/) (2019)
- [3DFR: A Swift 3D Feature Reductionist Framework for Scene Independent Change Detection](https://mlsanity.com/paper/1912.11891/) (2019)
- [Gasformer: A Transformer-based Architecture for Segmenting Methane Emissions from Livestock in Optical Gas Imaging](https://mlsanity.com/paper/2404.10841/) (2024)
- [Invisible Gas Detection: An RGB-Thermal Cross Attention Network and A New Benchmark](https://mlsanity.com/paper/2403.17712/) (2024)

## Built on by (most cited first, 6 of 6)

- [ZS-VCOS: Zero-Shot Video Camouflaged Object Segmentation By Optical Flow and Open Vocabulary Object Detection](https://mlsanity.com/paper/2505.01431/) (2025)
- [CarboFormer: A Lightweight Semantic Segmentation Architecture for Efficient Carbon Dioxide Detection Using Optical Gas Imaging](https://mlsanity.com/paper/2506.05360/) (2025)
- [JVLGS: Joint Vision-Language Gas Leak Segmentation](https://mlsanity.com/paper/2508.19485/) (2025)
- [Edge-Aware and Content-Adaptive Infrared Gas Leak Detection for Industrial Safety Monitoring](https://mlsanity.com/paper/2512.23234/) (2025)
- [OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection](https://mlsanity.com/paper/2601.22685/) (2026)
- [MissingBench-Verified: Probing Vision-Language Models' Inability to Detect Missing Object Parts](https://mlsanity.com/paper/2607.18673/) (2026)

## Abstract (arXiv)

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, SimGas, 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%. We also present an analysis of various prompt configurations and threshold settings to provide deeper insights into the performance of our method. Finally, we qualitatively (because of the lack of ground truth) tested our performance on GasVid and reached decent results on the real-world dataset. The dataset, code, and full qualitative results are available at https://github.com/weathon/Lang-Gas.