Pre-processing training data improves accuracy and generalisability of
convolutional neural network based landscape semantic segmentation
- URL: http://arxiv.org/abs/2304.14625v1
- Date: Fri, 28 Apr 2023 04:38:45 GMT
- Title: Pre-processing training data improves accuracy and generalisability of
convolutional neural network based landscape semantic segmentation
- Authors: Andrew Clark, Stuart Phinn, Peter Scarth
- Abstract summary: We trialled different methods of data preparation for CNN training and semantic segmentation of land use land cover (LULC) features within aerial photography over the Wet Tropics and Atherton Tablelands, Queensland, Australia.
This was conducted through trialling and ranking various training patch selection sampling strategies, patch and batch sizes and data augmentations and scaling.
We fully trained five models on the 2018 training image and applied the model to the 2015 test image with the output LULC classifications achieving an average of 0.84 user accuracy of 0.81 and producer accuracy of 0.87.
- Score: 2.8747398859585376
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In this paper, we trialled different methods of data preparation for
Convolutional Neural Network (CNN) training and semantic segmentation of land
use land cover (LULC) features within aerial photography over the Wet Tropics
and Atherton Tablelands, Queensland, Australia. This was conducted through
trialling and ranking various training patch selection sampling strategies,
patch and batch sizes and data augmentations and scaling. We also compared
model accuracy through producing the LULC classification using a single pass of
a grid of patches and averaging multiple grid passes and three rotated version
of each patch. Our results showed: a stratified random sampling approach for
producing training patches improved the accuracy of classes with a smaller area
while having minimal effect on larger classes; a smaller number of larger
patches compared to a larger number of smaller patches improves model accuracy;
applying data augmentations and scaling are imperative in creating a
generalised model able to accurately classify LULC features in imagery from a
different date and sensor; and producing the output classification by averaging
multiple grids of patches and three rotated versions of each patch produced and
more accurate and aesthetic result. Combining the findings from the trials, we
fully trained five models on the 2018 training image and applied the model to
the 2015 test image with the output LULC classifications achieving an average
kappa of 0.84 user accuracy of 0.81 and producer accuracy of 0.87. This study
has demonstrated the importance of data pre-processing for developing a
generalised deep-learning model for LULC classification which can be applied to
a different date and sensor. Future research using CNN and earth observation
data should implement the findings of this study to increase LULC model
accuracy and transferability.
Related papers
- Test-time adaptation for geospatial point cloud semantic segmentation with distinct domain shifts [6.80671668491958]
Test-time adaptation (TTA) allows direct adaptation of a pre-trained model to unlabeled data during inference stage without access to source data or additional training.
We propose three domain shift paradigms: photogrammetric to airborne LiDAR, airborne to mobile LiDAR, and synthetic to mobile laser scanning.
Experimental results show our method improves classification accuracy by up to 20% mIoU, outperforming other methods.
arXiv Detail & Related papers (2024-07-08T15:40:28Z) - Geometric Data Augmentations to Mitigate Distribution Shifts in Pollen
Classification from Microscopic Images [4.545340728210854]
We leverage the domain knowledge that geometric features are highly important for accurate pollen identification.
We introduce two novel geometric image augmentation techniques to significantly narrow the accuracy gap between the model performance on the train and test datasets.
arXiv Detail & Related papers (2023-11-18T10:35:18Z) - The Languini Kitchen: Enabling Language Modelling Research at Different
Scales of Compute [66.84421705029624]
We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours.
We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length.
This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
arXiv Detail & Related papers (2023-09-20T10:31:17Z) - The effect of data augmentation and 3D-CNN depth on Alzheimer's Disease
detection [51.697248252191265]
This work summarizes and strictly observes best practices regarding data handling, experimental design, and model evaluation.
We focus on Alzheimer's Disease (AD) detection, which serves as a paradigmatic example of challenging problem in healthcare.
Within this framework, we train predictive 15 models, considering three different data augmentation strategies and five distinct 3D CNN architectures.
arXiv Detail & Related papers (2023-09-13T10:40:41Z) - Neural Priming for Sample-Efficient Adaptation [92.14357804106787]
We propose Neural Priming, a technique for adapting large pretrained models to distribution shifts and downstream tasks.
Neural Priming can be performed at test time, even for pretraining as large as LAION-2B.
arXiv Detail & Related papers (2023-06-16T21:53:16Z) - Leveraging Angular Information Between Feature and Classifier for
Long-tailed Learning: A Prediction Reformulation Approach [90.77858044524544]
We reformulate the recognition probabilities through included angles without re-balancing the classifier weights.
Inspired by the performance improvement of the predictive form reformulation, we explore the different properties of this angular prediction.
Our method is able to obtain the best performance among peer methods without pretraining on CIFAR10/100-LT and ImageNet-LT.
arXiv Detail & Related papers (2022-12-03T07:52:48Z) - Scaling Laws for the Few-Shot Adaptation of Pre-trained Image
Classifiers [11.408339220607251]
Empirical science of neural scaling laws is a rapidly growing area of significant importance to the future of machine learning.
Our main goal is to investigate how the amount of pre-training data affects the few-shot generalization performance of standard image classifiers.
arXiv Detail & Related papers (2021-10-13T19:07:01Z) - Calibrating Class Activation Maps for Long-Tailed Visual Recognition [60.77124328049557]
We present two effective modifications of CNNs to improve network learning from long-tailed distribution.
First, we present a Class Activation Map (CAMC) module to improve the learning and prediction of network classifiers.
Second, we investigate the use of normalized classifiers for representation learning in long-tailed problems.
arXiv Detail & Related papers (2021-08-29T05:45:03Z) - Sparse Signal Models for Data Augmentation in Deep Learning ATR [0.8999056386710496]
We propose a data augmentation approach to incorporate domain knowledge and improve the generalization power of a data-intensive learning algorithm.
We exploit the sparsity of the scattering centers in the spatial domain and the smoothly-varying structure of the scattering coefficients in the azimuthal domain to solve the ill-posed problem of over-parametrized model fitting.
arXiv Detail & Related papers (2020-12-16T21:46:33Z) - Fast-Convergent Federated Learning [82.32029953209542]
Federated learning is a promising solution for distributing machine learning tasks through modern networks of mobile devices.
We propose a fast-convergent federated learning algorithm, called FOLB, which performs intelligent sampling of devices in each round of model training.
arXiv Detail & Related papers (2020-07-26T14:37:51Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.