# An Iteratively Optimized Patch Label Inference Network for Automatic Pavement Distress Detection

arXiv: https://arxiv.org/abs/2005.13298 · HTML: https://mlsanity.com/paper/2005.13298/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2020.

## Built on by (most cited first, 7 of 7)

- [Road Surface Defect Detection -- From Image-based to Non-image-based: A Survey](https://mlsanity.com/paper/2402.04297/) (2024)
- [Deep Domain Adaptation for Pavement Crack Detection](https://mlsanity.com/paper/2111.10101/) (2021)
- [Weakly Supervised Patch Label Inference Networks for Efficient Pavement Distress Detection and Recognition in the Wild](https://mlsanity.com/paper/2203.16782/) (2022)
- [Vehicular Road Crack Detection with Deep Learning: A New Online Benchmark for Comprehensive Evaluation of Existing Algorithms](https://mlsanity.com/paper/2503.18082/) (2025)
- [M2S-RoAD: Multi-Modal Semantic Segmentation for Road Damage Using Camera and LiDAR Data](https://mlsanity.com/paper/2504.10123/) (2025)
- [What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies](https://mlsanity.com/paper/2507.06513/) (2025)
- [PicT: A Slim Weakly Supervised Vision Transformer for Pavement Distress Classification](https://mlsanity.com/paper/2209.10074/) (2022)

## Abstract (arXiv)

We present a novel deep learning framework named the Iteratively Optimized Patch Label Inference Network (IOPLIN) for automatically detecting various pavement distresses that are not solely limited to specific ones, such as cracks and potholes. IOPLIN can be iteratively trained with only the image label via the Expectation-Maximization Inspired Patch Label Distillation (EMIPLD) strategy, and accomplish this task well by inferring the labels of patches from the pavement images. IOPLIN enjoys many desirable properties over the state-of-the-art single branch CNN models such as GoogLeNet and EfficientNet. It is able to handle images in different resolutions, and sufficiently utilize image information particularly for the high-resolution ones, since IOPLIN extracts the visual features from unrevised image patches instead of the resized entire image. Moreover, it can roughly localize the pavement distress without using any prior localization information in the training phase. In order to better evaluate the effectiveness of our method in practice, we construct a large-scale Bituminous Pavement Disease Detection dataset named CQU-BPDD consisting of 60,059 high-resolution pavement images, which are acquired from different areas at different times. Extensive results on this dataset demonstrate the superiority of IOPLIN over the state-of-the-art image classification approaches in automatic pavement distress detection. The source codes of IOPLIN are released on urlhttps://github.com/DearCaat/ioplin, and the CQU-BPDD dataset is able to be accessed on urlhttps://dearcaat.github.io/CQU-BPDD/.