Journal
XXIV ISPRS CONGRESS IMAGING TODAY, FORESEEING TOMORROW, COMMISSION II
Volume 5-2, Issue -, Pages 275-282Publisher
COPERNICUS GESELLSCHAFT MBH
DOI: 10.5194/isprs-annals-V-2-2022-275-2022
Keywords
Deep Learning; Semantic Segmentation; Label Noise; Very High Resolution
Funding
- Department of Science and Technology (DST), Government of India
- Dutch Research Council (NWO) [W 07.7019.103-DST-1429-WRC]
Ask authors/readers for more resources
This paper investigates the impact of label noise on the performance of deep learning models in semantic segmentation. Experimental results show that label noise decreases the accuracy of the model, and different classes respond differently to label noise.
The performance of deep learning models in semantic segmentation is dependent on the availability of a large amount of labeled data. However, the influence of label noise, in the form of incorrect annotations, on the performance is significant and mostly ignored. This is a big concern in remote sensing applications, wherein acquired datasets are spatially limited, labeling is done by domain experts with possible sources of high inter-and intra-observer variability leading to erroneous predictions. In this paper, we first simulate the label noise while conducting experiments on two different datasets with very high-resolution aerial images, height data, and inaccurate labels, responsible for the training of deep learning models. We then focus on the effect of these noises on the model performance. Different classes respond differently to the label noise. The typical size of an object belonging to a class is a crucial factor regarding the class-specific performance of the model trained with erroneous labels. Errors caused by relative shifts of labels are the most influential label errors. The model is generally more tolerant of the random label noise than other label errors. It has been observed that the accuracy gets reduced by at least 3% while 5% of label pixels are erroneous. In this regard, our study provides a new perspective of evaluating and quantifying the propagation of label noise in the model performance that is indeed important for adopting reliable semantic segmentation practices.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available