# Distribution-aware Noisy-label Crack Segmentation

arXiv: https://arxiv.org/abs/2410.09409 · HTML: https://mlsanity.com/paper/2410.09409/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 41 references that are in the map.
- First posted on arXiv 12 Oct 2024.

## Builds on (most cited first, 21 of 21)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation](https://mlsanity.com/paper/1511.00561/) (2015)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [OneFormer: One Transformer to Rule Universal Image Segmentation](https://mlsanity.com/paper/2211.06220/) (2022)
- [Probabilistic End-to-end Noise Correction for Learning with Noisy Labels](https://mlsanity.com/paper/1903.07788/) (2019)
- [Selective-Supervised Contrastive Learning with Noisy Labels](https://mlsanity.com/paper/2203.04181/) (2022)
- [Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation](https://mlsanity.com/paper/2111.01236/) (2021)
- [GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Models](https://mlsanity.com/paper/2210.02025/) (2022)
- [Feature Pyramid and Hierarchical Boosting Network for Pavement Crack Detection](https://mlsanity.com/paper/1901.06340/) (2019)
- [Semantic Segmentation using Vision Transformers: A survey](https://mlsanity.com/paper/2305.03273/) (2023)
- [AVSegFormer: Audio-Visual Segmentation with Transformer](https://mlsanity.com/paper/2307.01146/) (2023)
- [EMCAD: Efficient Multi-scale Convolutional Attention Decoding for Medical Image Segmentation](https://mlsanity.com/paper/2405.06880/) (2024)
- [Learning Mixtures of Gaussians Using the DDPM Objective](https://mlsanity.com/paper/2307.01178/) (2023)
- [Asymmetric Loss Functions for Learning with Noisy Labels](https://mlsanity.com/paper/2106.03110/) (2021)
- [When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method](https://mlsanity.com/paper/2211.10955/) (2022)
- [Evaluating generative networks using Gaussian mixtures of image features](https://mlsanity.com/paper/2110.05240/) (2021)
- [Is your noise correction noisy? PLS: Robustness to label noise with two stage detection](https://mlsanity.com/paper/2210.04578/) (2022)
- [Computer-Aided Road Inspection: Systems and Algorithms](https://mlsanity.com/paper/2203.02355/) (2022)

## Abstract (arXiv)

Road crack segmentation is critical for robotic systems tasked with the inspection, maintenance, and monitoring of road infrastructures. Existing deep learning-based methods for crack segmentation are typically trained on specific datasets, which can lead to significant performance degradation when applied to unseen real-world scenarios. To address this, we introduce the SAM-Adapter, which incorporates the general knowledge of the Segment Anything Model (SAM) into crack segmentation, demonstrating enhanced performance and generalization capabilities. However, the effectiveness of the SAM-Adapter is constrained by noisy labels within small-scale training sets, including omissions and mislabeling of cracks. In this paper, we present an innovative joint learning framework that utilizes distribution-aware domain-specific semantic knowledge to guide the discriminative learning process of the SAM-Adapter. To our knowledge, this is the first approach that effectively minimizes the adverse effects of noisy labels on the supervised learning of the SAM-Adapter. Our experimental results on two public pavement crack segmentation datasets confirm that our method significantly outperforms existing state-of-the-art techniques. Furthermore, evaluations on the completely unseen CFD dataset demonstrate the high cross-domain generalization capability of our model, underscoring its potential for practical applications in crack segmentation.