Jul 2026· Signal, Image and Video Processing· Vol 20· 1 citation· 14 references
Computer Science
TL;DR
A novel deep learning framework that leverages image embeddings from a pre-trained SegFormer-B4 encoder (MiT-B4) without fine-tuning, combined with a U-Net decoder, to achieve precise water body segmentation in Sentinel-2 satellite imagery.
Abstract
Accurate segmentation of water bodies in satellite imagery is essential for environmental monitoring, resource management, and disaster response. This study introduces a novel deep learning framework that leverages image embeddings from a pre-trained SegFormer-B4 encoder (MiT-B4) without fine-tuning, combined with a U-Net decoder, to achieve precise water body segmentation in Sentinel-2 satellite imagery. Unlike conventional methods that rely on full fine-tuning, this approach significantly reduces computational cost and training time while maintaining high segmentation accuracy. The extracted transformer-based embeddings capture both local and global spatial features, serving as input to a lightweight U-Net decoder that efficiently reconstructs segmentation masks. Experimental results demonstrate that the proposed method outperforms the fine-tuned SegFormer-B4 model in training and testing scenarios, achieving superior Intersection over Union (IoU), F1 Score, Precision, and Recall. Despite the absence of fine-tuning, the SegFormer-B4 encoder effectively extracts meaningful spatial representations, enabling accurate segmentation with minimal computational overhead. This work highlights the advantages of integrating pre-trained transformer embeddings with a dedicated segmentation decoder, offering a scalable and efficient solution for water body mapping in remote sensing applications.
The proposed GeoRGMAE, a geospatially guided masked autoencoder pretraining strategy for building segmentation, introduces three masking strategies that prioritize semantically relevant building regions under the varying urban densities and suggests that incorporating geospatial priors into masked image modelling (MIM) can improve representation learning for downstream building segmentation tasks.
Tuğba Eraslanoğlu, G. Mutreja, Martin Kada et al.· The International Archives o...· 0 citations
Experimental results demonstrate that the adapted SAM2 model achieves stable segmentation under moderate environmental variability, while degrading under severe visibility loss, consistent across model scales and input resolutions.
Bindusara Nagathihalli Lokesh, Laura Camila Duran Vergara, Hans-Gerd Maas et al.· The International Archives o...· 1 citation
The results establish zero-shot NAS as a computationally efficient paradigm for large-scale Earth observation segmentation as a training-free strategy for semantic segmentation in Earth observation.
Gabriel Iuhasz, Marian Neagul· IEEE Access· 0 citations
Wildfire detection from satellite imagery is a semantic image segmentation problem that has proven to be difficult due to challenges such as class imbalance, feature complexity, and atmospheric interference. In this paper, we build on the foundational U-Net image segmentation model to develop a quantum-hybrid solution in hopes of more effectively modeling the high-dimensional spectral feature space of the Sen2Fire dataset. We inject a variational quantum circuit in the bottleneck portion of U-Net, specifically the QuFeX and QB-Net ansatzes. We test a classical Feature Pyramid Network (FPN) for further comparative analysis of the model, and we also explore classical improvements to the U-Net model and its training process, including a compression of parameters, alternative loss functions, and uniform mixing of input data. Our primary finding is that under matched conditions, both QB-Net (with an $F_1$ score of 31.18) and QuFeX ($F_1 = 30.79$) outperformed the classical U-Net baseline results ($F_1 = 28.71$). Additionally, the classical FPN achieved a comparable score of 31.13. A crucial finding was that data mixing removed a significant domain shift between the geographically-separated train and test sets, which boosted the classical FPN $F_1$ score to 39.76. We validate the architecture's robustness and generalizability to the wildfire detection problem via cross-dataset transfer on the California Burned Areas (CaBuAr) dataset. Overall, we find that quantum machine learning has potential to provide an advantage in the problem of wildfire image segmentation, and further experiments will continue to validate and expand upon this finding.
Jaiman Munshi, Tanvi Tewary, Sawyer Bloom et al.· 0 citations
Terraces constitute a critical form of land surface modification, serving both as essential agricultural resources and effective soil and water conservation measures. However, their morphological diversity, pronounced scale variation, and ambiguous geometric boundaries pose substantial challenges for automated extraction from high-resolution remote sensing imagery. Existing CNN- and Transformer-based methods still face difficulties in simultaneously preserving fine spatial details and modeling long-range contextual information. To address these limitations, this study proposes TerraceNet, a hybrid CNN–Transformer architecture with an encoder–dual-decoder design. The framework employs a ConvNeXt encoder to extract multi-scale features, which are subsequently aggregated by a dynamic fusion feature pyramid network (DF-FPN) and fed into two parallel decoders: a boundary decoder dedicated to fine-grained edge localization and a multi-scale Transformer decoder that incorporates boundary priors for global context modeling and final segmentation. Experimental results on a 2 m resolution GF-1 satellite imagery dataset from the Wuding River Basin in the Loess Plateau demonstrate that TerraceNet an IoU of 77.61% and an F1-Score of 87.39%. These results validate the effectiveness of the proposed architecture for extracting morphologically diverse terraces in complex terrain.
Fengying Jin, Zhihui Wang, Yinan Wang et al.· Remote Sensing· 0 citations
Abstract. Accurate land-cover maps are essential, but medium-resolution imagery (e.g., Sentinel-2 at 10 m) often contains mixed pixels that include multiple land-cover types. Standard “hard” classification assigns one class per pixel, hiding minority classes and reducing map usefulness. Compositional classification instead estimates the proportion of each class within a pixel, preserving sub-pixel detail, but requires outputs that are non-negative and sum to one, constraints not naturally handled by typical ML/DL losses. This study proposed and evaluated a deep-learning framework for compositional land-cover estimation at 10 m resolution. It compared two input feature sets: (1) reflectance from 10 Sentinel-2 multispectral bands (B2–B8, B8A, B11, B12) and (2) Embedding V1, a 64- dimensional representation from the AlphaEarth Foundations model that integrates multi-source, multi-temporal Earth observation signals. Ground-truth composition vectors were derived from OpenEarthMap by aggregating 0.25–0.5 m labels to 10 m pixels for eight classes. Three architectures (MLP, 2D-CNN, 3D-CNN) used Softmax outputs to enforce the constant-sum constraint, and two losses (MAE vs Aitchison distance) were tested. Embedding V1 improved estimation accuracy across all model architectures compared to Sentinel-2 spectral bands alone. While 3D-CNN achieved the best performance with Sentinel-2 input (MAE: 0.1126), MLP outperformed all other architectures when Embedding V1 was used (MAE: 0.0989). Comparison of fraction maps revealed that MAE produced spatially smoothed outputs, whereas Aitchison distance yielded sharper and more realistic compositions. The combination of Embedding V1, MLP, and Aitchison distance loss achieved the best overall performance, suggesting that foundation model embeddings combined with compositional losses can improve sub-pixel land-cover estimation.
Ayato Kanno, Narumasa Tsutsumida· The International Archives o...· 0 citations