MFALNet: A Multiscale Feature Aggregation Lightweight Network for Semantic Segmentation of High-Resolution Remote Sensing Images

Lv, Liang; Guo, Yiyou; Bao, Tengfei; Fu, Chenqin; Hu, Hong; Fang, Tao

doi:10.1109/lgrs.2020.3012705

Cited by 13 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The last class only appears in few training tiles and does not have a strong semantic meaning, since it includes all of the surface covers that do not belong to the other well-defined classes. Hence, it was removed from the experimentation (similar to previous works [22], [23]).…”

Section: Experimental Validationmentioning

confidence: 99%

Learning CRF potentials through fully convolutional networks for satellite image semantic segmentation

Pastorino,

Moser,

Serpico

et al. 2023

2023 17th International Conference on Signal-Image Technology &Amp;amp; Internet-Based Systems (SITIS)

View full text Add to dashboard Cite

This paper introduces a method to automatically learn the unary and pairwise potentials of a conditional random field (CRF) from the input data in a non-parametric fashion, within the framework of the semantic segmentation of remote sensing images. The proposed model is based on fully convolutional networks (FCNs) and fully connected neural networks (FCNNs) to extensively exploit the semantic and spatial information contained in the input data and in the intermediate layers of an FCN. The idea of the model is twofold: first to learn the statistics of a CRF via a convolutional layer, whose kernel defines the clique of interest, and, second, to favor the interpretability of the intermediate layers as posterior probabilities through the FCNNs. The method was tested with the ISPRS 2D Semantic Labeling Challenge Vaihingen dataset, after modifying the ground truths to approximate the ones found in realistic remote sensing applications, characterized by scarce and spatially non-exhaustive annotations. The results confirm the effectiveness of the proposed technique for the semantic segmentation of satellite images.

show abstract

Section: Experimental Validationmentioning

confidence: 99%

Learning CRF potentials through fully convolutional networks for satellite image semantic segmentation

Pastorino,

Moser,

Serpico

et al. 2023

2023 17th International Conference on Signal-Image Technology &Amp;amp; Internet-Based Systems (SITIS)

View full text Add to dashboard Cite

show abstract

“…The ISPRS Potsdam dataset contains 38 images with IRRG channels at a spatial resolution of 5 cm and of size 6000 As previously done by other authors in [46], [47], [48], the results for the clutter class, which includes all covers that are not attributed to the other classes and mixes water bodies, background, and others in the same thematic class, were excluded from the averaged metrics. This class accounts for only a small percentage of pixels.…”

Section: A Datasetsmentioning

confidence: 99%

Semantic Segmentation of Remote-Sensing Images Through Fully Convolutional Neural Networks and Hierarchical Probabilistic Graphical Models

Pastorino

Moser

Zerubia

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Deep learning is currently the dominant approach to image classification and segmentation, but the performances of deep learning methods are remarkably influenced by the quantity and quality of the ground truth (GT) used for training. In this paper, a deep learning method is presented to deal with the semantic segmentation of very high resolution (VHR) remote sensing data in the case of scarce GT. The main idea is to combine a specific type of deep convolutional neural networks (CNNs), namely, fully convolutional networks (FCNs), with probabilistic graphical models (PGMs). Our method takes advantage of the intrinsic multiscale behavior of FCNs to deal with multiscale data representations and to connect them to a hierarchical Markov model (e.g., making use of a quadtree). As a consequence, the spatial information present in the data is better exploited, allowing a reduced sensitivity to GT incompleteness to be obtained. The marginal posterior mode criterion is used for inference in the proposed framework. To assess the capabilities of the proposed method, the experimental validation is conducted with the ISPRS 2D Semantic Labeling Challenge datasets on the cities of Vaihingen and Potsdam, with some modifications to simulate the spatially sparse GTs that are common in real remote sensing applications. The results are quite significant, as the proposed approach exhibits a higher producer accuracy than the standard FCNs considered and especially mitigates the impact of scarce GTs on minority classes and small spatial details.

show abstract

“…Furthermore, it accounts for only a small percentage of pixels. Following the example of previous authors [18,19,20], the results of the class "clutter" were excluded from the averaged metrics.…”

Section: Experimental Validationmentioning

confidence: 99%

Fully Convolutional and Feedforward Networks for The Semantic Segmentation of Remotely Sensed Images

Pastorino

Moser

Serpico

et al. 2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

This paper presents a novel semantic segmentation method of very high resolution remotely sensed images based on fully convolutional networks (FCNs) and feedforward neural networks (FFNNs). The proposed model aims to exploit the intrinsic multiscale information extracted at different convolutional blocks in an FCN by the integration of FFNNs, thus incorporating information at different scales. The purpose is to obtain accurate classification results with realistic data sets characterized by sparse ground truth (GT) data by taking benefit from multiscale and long-range spatial information. The final loss function is computed as a linear combination of the weighted cross-entropy losses of the FFNNs and of the FCN. The modeling of spatial-contextual information is further addressed by the introduction of an additional loss term which allows to integrate spatial information between neighboring pixels. The experimental validation is conducted with the ISPRS 2D Semantic Labeling Challenge data set over the city of Vaihingen, Germany. The results are promising, as the proposed approach obtains higher average classification results than the state-of-the-art techniques considered, especially in the case of scarce, suboptimal GTs.

show abstract

MFALNet: A Multiscale Feature Aggregation Lightweight Network for Semantic Segmentation of High-Resolution Remote Sensing Images

Cited by 13 publications

References 11 publications

Learning CRF potentials through fully convolutional networks for satellite image semantic segmentation

Learning CRF potentials through fully convolutional networks for satellite image semantic segmentation

Semantic Segmentation of Remote-Sensing Images Through Fully Convolutional Neural Networks and Hierarchical Probabilistic Graphical Models

Fully Convolutional and Feedforward Networks for The Semantic Segmentation of Remotely Sensed Images

Contact Info

Product

Resources

About