# CrackNex: a Few-shot Low-light Crack Segmentation Model Based on Retinex Theory for UAV Inspections

arXiv: https://arxiv.org/abs/2403.03063 · HTML: https://mlsanity.com/paper/2403.03063/

## Key facts

- Cited by 12 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 5 Mar 2024.

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

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment](https://mlsanity.com/paper/1908.06391/) (2019)
- [Few-Shot Learning with Graph Neural Networks](https://mlsanity.com/paper/1711.04043/) (2017)
- [Meta Networks](https://mlsanity.com/paper/1703.00837/) (2017)
- [Hypercorrelation Squeeze for Few-Shot Segmentation](https://mlsanity.com/paper/2104.01538/) (2021)
- [Rethinking BiSeNet For Real-time Semantic Segmentation](https://mlsanity.com/paper/2104.13188/) (2021)
- [Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2207.10866/) (2022)
- [Self-Support Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2207.11549/) (2022)
- [Few-shot 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2006.12052/) (2020)
- [Meta-Learning of Neural Architectures for Few-Shot Learning](https://mlsanity.com/paper/1911.11090/) (2019)
- [Mining Latent Classes for Few-shot Segmentation](https://mlsanity.com/paper/2103.15402/) (2021)
- [LiDAR Distillation: Bridging the Beam-Induced Domain Gap for 3D Object Detection](https://mlsanity.com/paper/2203.14956/) (2022)
- [Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning](https://mlsanity.com/paper/2110.03909/) (2021)
- [Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding](https://mlsanity.com/paper/2012.05440/) (2020)
- [Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation](https://mlsanity.com/paper/2106.06908/) (2021)
- [PP-LiteSeg: A Superior Real-Time Semantic Segmentation Model](https://mlsanity.com/paper/2204.02681/) (2022)
- [SATS: Self-Attention Transfer for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.07667/) (2022)
- [Interclass Prototype Relation for Few-Shot Segmentation](https://mlsanity.com/paper/2211.08681/) (2022)
- [CrackSeg9k: A Collection and Benchmark for Crack Segmentation Datasets and Frameworks](https://mlsanity.com/paper/2208.13054/) (2022)
- [Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Images](https://mlsanity.com/paper/2306.07598/) (2023)
- [LanDA: Language-Guided Multi-Source Domain Adaptation](https://mlsanity.com/paper/2401.14148/) (2024)
- [Optimized Deep Encoder-Decoder Methods for Crack Segmentation](https://mlsanity.com/paper/2008.06266/) (2020)
- [Real-time High-Resolution Neural Network with Semantic Guidance for Crack Segmentation](https://mlsanity.com/paper/2307.00270/) (2023)
- [Topic Driven Adaptive Network for Cross-Domain Sentiment Classification](https://mlsanity.com/paper/2111.14094/) (2021)
- [Pavement Distress Detection and Segmentation using YOLOv4 and DeepLabv3 on Pavements in the Philippines](https://mlsanity.com/paper/2103.06467/) (2021)

## Built on by (most cited first, 12 of 12)

- [Endora: Video Generation Models as Endoscopy Simulators](https://mlsanity.com/paper/2403.11050/) (2024)
- [Real-Time Pill Identification for the Visually Impaired Using Deep Learning](https://mlsanity.com/paper/2405.05983/) (2024)
- [Event-guided Low-light Video Semantic Segmentation](https://mlsanity.com/paper/2411.00639/) (2024)
- [Staircase Cascaded Fusion of Lightweight Local Pattern Recognition and Long-Range Dependencies for Structural Crack Segmentation](https://mlsanity.com/paper/2408.12815/) (2024)
- [Cognitive-Inspired Hierarchical Attention Fusion With Visual and Textual for Cross-Domain Sequential Recommendation](https://mlsanity.com/paper/2504.15085/) (2025)
- [BeltCrack: the First Sequential-image Industrial Conveyor Belt Crack Detection Dataset and Its Baseline with Triple-domain Feature Learning](https://mlsanity.com/paper/2506.17892/) (2025)
- [Deep Learning for Crack Detection: A Review of Learning Paradigms, Generalizability, and Datasets](https://mlsanity.com/paper/2508.10256/) (2025)
- [ReVA: A Scene-Centric Dataset Beyond Repetition for Remote Sensing Video Question Answering](https://mlsanity.com/paper/2609.35507/) (2026)
- [Prototype Learning-Based Few-Shot Segmentation for Low-Light Crack on Concrete Structures](https://mlsanity.com/paper/2601.13059/) (2026)
- [Robust Lightweight Crack Classification for Real-Time UAV Bridge Inspection](https://mlsanity.com/paper/2604.27617/) (2026)
- [Multi-Task Crack Foundation Model for Engineering-Reliable Crack Representation and Topology Preservation in Civil Infrastructure](https://mlsanity.com/paper/2606.05641/) (2026)
- [Bridge Damage Detection from Low-Light UAV Imagery via Degradation-Aware Mixture-of-Experts Enhancement](https://mlsanity.com/paper/2608.23136/) (2026)

## Abstract (arXiv)

Routine visual inspections of concrete structures are imperative for upholding the safety and integrity of critical infrastructure. Such visual inspections sometimes happen under low-light conditions, e.g., checking for bridge health. Crack segmentation under such conditions is challenging due to the poor contrast between cracks and their surroundings. However, most deep learning methods are designed for well-illuminated crack images and hence their performance drops dramatically in low-light scenes. In addition, conventional approaches require many annotated low-light crack images which is time-consuming. In this paper, we address these challenges by proposing CrackNex, a framework that utilizes reflectance information based on Retinex Theory to help the model learn a unified illumination-invariant representation. Furthermore, we utilize few-shot segmentation to solve the inefficient training data problem. In CrackNex, both a support prototype and a reflectance prototype are extracted from the support set. Then, a prototype fusion module is designed to integrate the features from both prototypes. CrackNex outperforms the SOTA methods on multiple datasets. Additionally, we present the first benchmark dataset, LCSD, for low-light crack segmentation. LCSD consists of 102 well-illuminated crack images and 41 low-light crack images. The dataset and code are available at https://github.com/zy1296/CrackNex.