TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

Vasu, Subeesh; Koziński, Mateusz; Citraro, Leonardo; Fua, Pascal

doi:10.1007/978-3-030-58583-9_14

Cited by 8 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[53] offered a point-based iterative graph exploration scheme to boost the model's perception of global information, thereby enhancing overall segmentation results. [55] observed that conventional CNN-based methods fail to preserve global road connectivity because these networks typically utilize pixel-wise losses for optimization. [35] developed a strip convolution module to capture long-range contextual information from various directions, which significantly improved the connectivity of segmentation results, as demonstrated by this method's high performance on the DeepGlobe dataset [35].…”

Section: Related Workmentioning

confidence: 99%

An Enhanced Loss Function for Semantic Road Segmentation in Remote Sensing Images

Nanni,

Brahnam,

Loreggia

2024

IEEE Access

View full text Add to dashboard Cite

The analysis of road continuity in satellite images is a complex challenge. This is due to the difficulty in identifying the directional vector of road sections, especially when the satellite view of roads is obstructed by trees or other structures. Today, most research focuses on optimizing the deep learning network topology, however, the accuracy of segmentation is affected by the loss function used in training; currently, little research has been published on ad-hoc loss functions for road segmentation.To solve this problem, we proposed loss functions based on topological pixel analysis, in which more weight is given to problematic pixels representing non-real road breaks. We report the results of different tests, obtaining state-of-the-art performance among convolution neural network based approaches. Both the code and information for replicating our experiments are available on https://github.com/LorisNanni/An-Enhanced-Loss-Function-for-Semantic-Road-Segmentation-in-Remote-Sensing-Images , so as to enable future reliable comparisons.

show abstract

Section: Related Workmentioning

confidence: 99%

An Enhanced Loss Function for Semantic Road Segmentation in Remote Sensing Images

Nanni,

Brahnam,

Loreggia

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…21 Balancing two loss functions is difficult, resulting in unstable and often poor training. Vasu et al 22 emphasized that the discriminator of the standard GAN does not capture the local segmentation errors. The results of Reti-naGAN and SUD-GAN are not outstanding.…”

Section: Related Workmentioning

confidence: 99%

Improving sensitivity and connectivity of retinal vessel segmentation via error discrimination network

et al. 2022

View full text Add to dashboard Cite

Purpose Automated retinal vessel segmentation is crucial to the early diagnosis and treatment of ophthalmological diseases. Many deep‐learning‐based methods have shown exceptional success in this task. However, current approaches are still inadequate in challenging vessels (e.g., thin vessels) and rarely focus on the connectivity of vessel segmentation. Methods We propose using an error discrimination network (D) to distinguish whether the vessel pixel predictions of the segmentation network (S) are correct, and S is trained to obtain fewer error predictions of D. Our method is similar to, but not the same as, the generative adversarial network. Three types of vessel samples and corresponding error masks are used to train D, as follows: (1) vessel ground truth; (2) vessel segmented by S; (3) artificial thin vessel error samples that further improve the sensitivity of D to wrong small vessels. As an auxiliary loss function of S, D strengthens the supervision of difficult vessels. Optionally, we can use the errors predicted by D to correct the segmentation result of S. Results Compared with state‐of‐the‐art methods, our method achieves the highest scores in sensitivity (86.19%, 86.26%, and 86.53%) and G‐Mean (91.94%, 91.30%, and 92.76%) on three public datasets, namely, STARE, DRIVE, and HRF. Our method also maintains a competitive level in other metrics. On the STARE dataset, the F1‐score and area under the receiver operating characteristic curve (AUC) of our method rank second and first, respectively, reaching 84.51% and 98.97%. The top scores of the three topology‐relevant metrics (Conn, Inf, and Cor) demonstrate that the vessels extracted by our method have excellent connectivity. We also validate the effectiveness of error discrimination supervision and artificial error sample training through ablation experiments. Conclusions The proposed method provides an accurate and robust solution for difficult vessel segmentation.

show abstract

Detection of road extraction from satellite images with deep learning method

Aslan,

Özüpak

2024

Cluster Comput

View full text Add to dashboard Cite

TopoAL: An Adversarial Learning Approach for Topology-Aware Road Segmentation

Cited by 8 publications

References 27 publications

An Enhanced Loss Function for Semantic Road Segmentation in Remote Sensing Images

An Enhanced Loss Function for Semantic Road Segmentation in Remote Sensing Images

Improving sensitivity and connectivity of retinal vessel segmentation via error discrimination network

Detection of road extraction from satellite images with deep learning method

Contact Info

Product

Resources

About