Enhancing DeepLabV3+ to Fuse Aerial and Satellite Images for Semantic Segmentation
Not on the map. Why?
Abstract (arXiv)
Aerial and satellite imagery are inherently complementary remote sensing sources, offering high-resolution detail alongside expansive spatial coverage. However, the use of these sources for land cover segmentation introduces several challenges, prompting the development of a variety of segmentation methods. Among these approaches, the DeepLabV3+ architecture is considered as a promising approach in the field of single-source image segmentation. However, despite its reliable results for segmentation, there is still a need to increase its robustness and improve its performance. This is particularly crucial for multimodal image segmentation, where the fusion of diverse types of information is essential. An interesting approach involves enhancing this architectural framework through the integration of novel components and the modification of certain internal processes. In this paper, we enhance the DeepLabV3+ architecture by introducing a new transposed conventional layers block for upsampling a second entry to fuse it with high level features. This block is designed to amplify and integrate information from satellite images, thereby enriching the segmentation process through fusion with aerial images. For experiments, we used the LandCover.ai (Land Cover from Aerial Imagery) dataset for aerial images, alongside the corresponding dataset sourced from Sentinel 2 data. Through the fusion of both sources, the mean Intersection over Union (mIoU) achieved a total mIoU of 84.91% without data augmentation.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 21 of its 54 references that are in the map. First posted on arXiv 28 Mar 2025.
Builds on
21 of 54 references.
References · 21
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
- 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
- 2018ESRGAN: Enhanced Super-Resolution Generative Adversarial Networkscited by 1,250
- 2014Image Super-Resolution Using Deep Convolutional Networkscited by 1,218
- 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,199
- 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,061
- 2021UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene Imagerycited by 166
- 2019Benchmarking the Robustness of Semantic Segmentation Modelscited by 111
9 more
- 2018Searching for Efficient Multi-Scale Architectures for Dense Image Predictioncited by 96
- 2021Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer visioncited by 76
- 2023Semantic Segmentation using Vision Transformers: A surveycited by 73
- 2015Hyperspectral pansharpening: a reviewcited by 55
- 2020LandCover.ai: Dataset for Automatic Mapping of Buildings, Woodlands, Water and Roads from Aerial Imagerycited by 40
- 2021Pansharpening by convolutional neural networks in the full resolution frameworkcited by 15
- 2018Multisource and Multitemporal Data Fusion in Remote Sensingcited by 8
- 2020VddNet: Vine Disease Detection Network Based on Multispectral Images and Depth Mapcited by 2
- 2023DeepTriNet: A Tri-Level Attention Based DeepLabv3+ Architecture for Semantic Segmentation of Satellite Imagescited by 2
Built on by
Not cited yet.