EVALUATION OF UNet AND UNet++ ARCHITECTURES IN HIGH RESOLUTION IMAGE CHANGE DETECTION APPLICATIONS

Alexakis, E. Bousias; Armenakis, Costas

doi:10.5194/isprs-archives-xliii-b3-2020-1507-2020

Cited by 31 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[10] use a fully convolutional CNN and the EF scheme, obtaining results that are superior to those reported in [9]. Other works rely on different FC architectures, such as U-net [53], [54] and DeepLabv3+ [12]. The latter compares PWC and FC-based approaches applied to deforestation detection, concluding that the FC classification scheme generally deliveres higher accuracies.…”

Section: A Deep Learning For Change Detectionmentioning

confidence: 95%

Weakly Supervised Domain Adversarial Neural Network for Deforestation Detection in Tropical Forests

Vega,

da Costa,

Adarme

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Domain adaptation has proven to be suitable for alleviating domain discrepancies, which hinder the generalization capacity of classifiers. Among a few alternatives, domain adaptation techniques that align features in a domain-agnostic space through adversarial learning have been widely investigated. Nevertheless, such an approach often implies the deterioration of feature discriminability as a side effect of the adversarial alignment, which does not take into consideration class labels of the target domain samples. We advocate that weakly-supervised learning can help mitigate that problem, as noisy labels for the target domain samples may serve to sustain class discriminability during the feature alignment procedure. Therefore, in this work we propose a weakly-supervised, adversarial domain adaptation method for a change detection task based on the Domain Adversarial Neural Network (DANN) strategy. We assessed the performance of the proposed method on a deforestation detection application, conducting experiments in sites of the Amazon and Cerrado (Brazilian Savannah) biomes using Landsat-8 images, each site corresponding to a different domain. The results showed that the inclusion of weak supervision in the domain adaptation procedure provided higher accuracies as compared to the original DANN strategy, which did not prescribe any supervision for the selection of target domain samples in the training procedure. On average, the Average Precision and F1-score metrics values increased by 10.1% and 12.6% respectively with the use of the proposed method. Additionally, our method achieved performances that are compatible with the ones obtained with previously proposed, state-of-the-art domain adaptation methods. To the best of our knowledge, the proposed method is the first weakly-supervised domain adaptation strategy conceived for deforestation detection and, in general, for change detection.

show abstract

Section: A Deep Learning For Change Detectionmentioning

confidence: 95%

Weakly Supervised Domain Adversarial Neural Network for Deforestation Detection in Tropical Forests

Vega,

da Costa,

Adarme

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…14 This model was first introduced in the year of 2015 by Ronneberger et al, 11 and it has been used in a wide range of medical image segmentation applications. [15][16][17] U-Net architecture is a fully convolutional neural network (FCN), consisting of an encoder and a decoder path, and level-wise skip connections. Several research works have proposed modifications to the vanilla U-Net architecture over time, mostly to improve its performance on very specific medical image segmentation tasks.…”

Section: Related Workmentioning

confidence: 99%

U-PEN++: redesigning U-PEN architecture with multi-head attention for retinal image segmentation

Sidike

Reyes

Devagiri

et al. 2023

Pattern Recognition and Tracking XXXIV

View full text Add to dashboard Cite

In the era of the ever-increasing need for computing power, deep learning (DL) algorithms are becoming critical for accomplishing success in various domains, such as accessibility and processing of information from the quantum of data present in the physical, digital, and biological realms. Medical image segmentation is one such application of DL in the healthcare sector. The segmentation of medical images, such as retinal images, enables an efficient analytical process for diagnostics and medical procedures. To segment regions of interest in medical images, U-Net has been primarily used as the baseline DL architecture that consists of contracting and expanding paths for capturing semantic features and precision localization. Although several forms of U-Net have shown promise, its limitations such as hardware memory requirements and inaccurate localization of nonstandard shapes still need to be addressed effectively. In this work, we propose U-PEN++, which reconfigures previously developed U-PEN (U-Net with Progressively Expanded Neuron) architecture by introducing a new module named Progressively Expanded Neuron with Attention (PEN-A) that consists of Maclaurin Series of a nonlinear function and multi-head attention mechanism. The proposed PEN-A module enriches the feature representation by capturing more relevant contextual information when compared to the U-PEN model. Moreover, the proposed model removes excessive hidden layers, resulting in less trainable parameters when compared to U-PEN. Experimental analysis performed on DRIVE and CHASE datasets demonstrated more effective segmentation and parameter efficiency of the proposed U-PEN++ architecture for retinal image segmentation tasks when compared to U-Net, U-PEN, and Residual U-Net architectures.

show abstract

“…Our rationale for choosing the Dice loss function is to enhance the overlap between predicted and actual segmented regions, consequently improving segmentation accuracy. In our deep learning model training, we utilized the Dice loss [43] as the primary loss function.…”

Section: Experimental Strategymentioning

confidence: 99%

Fusing Ascending and Descending Time-Series SAR Images with Dual-Polarized Pixel Attention UNet for Landslide Recognition

Pan,

Shi

2023

Remote Sensing

View full text Add to dashboard Cite

Conducting landslide recognition research holds notable practical significance for disaster management. In response to the challenges posed by noise, information redundancy, and geometric distortions in single-orbit SAR imagery during landslide recognition, this study proposes a dual-polarization SAR image landslide recognition approach that combines ascending and descending time-series information while considering polarization channel details to enhance the accuracy of landslide identification. The results demonstrate notable improvements in landslide recognition accuracy using the ascending and descending fusion strategy compared to single-orbit data, with F1 scores increasing by 5.19% and 8.82% in Hokkaido and Papua New Guinea, respectively. Additionally, utilizing time-series imagery in Group 2 as opposed to using only pre- and post-event images in Group 4 leads to F1 score improvements of 6.94% and 9.23% in Hokkaido and Papua New Guinea, respectively, confirming the effectiveness of time-series information in enhancing landslide recognition accuracy. Furthermore, employing dual-polarization strategies in Group 4 relative to single-polarization Groups 5 and 6 results in peak F1 score increases of 7.46% and 12.07% in Hokkaido and Papua New Guinea, respectively, demonstrating the feasibility of dual-polarization strategies. However, due to limitations in Sentinel-1 imagery resolution and terrain complexities, omissions and false alarms may arise near landslide edges. The improvements achieved in this study hold critical implications for landslide disaster assessment and provide valuable insights for further enhancing landslide recognition capabilities.

show abstract

EVALUATION OF UNet AND UNet++ ARCHITECTURES IN HIGH RESOLUTION IMAGE CHANGE DETECTION APPLICATIONS

Cited by 31 publications

References 12 publications

Weakly Supervised Domain Adversarial Neural Network for Deforestation Detection in Tropical Forests

Weakly Supervised Domain Adversarial Neural Network for Deforestation Detection in Tropical Forests

U-PEN++: redesigning U-PEN architecture with multi-head attention for retinal image segmentation

Fusing Ascending and Descending Time-Series SAR Images with Dual-Polarized Pixel Attention UNet for Landslide Recognition

Contact Info

Product

Resources

About