skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Attention:

The NSF Public Access Repository (PAR) system and access will be unavailable from 11:00 PM ET on Friday, November 14 until 2:00 AM ET on Saturday, November 15 due to maintenance. We apologize for the inconvenience.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: AerialFormer: Multi-Resolution Transformer for Aerial Image Segmentation
When performing remote sensing image segmentation, practitioners often encounter various challenges, such as a strong imbalance in the foreground–background, the presence of tiny objects, high object density, intra-class heterogeneity, and inter-class homogeneity. To overcome these challenges, this paper introduces AerialFormer, a hybrid model that strategically combines the strengths of Transformers and Convolutional Neural Networks (CNNs). AerialFormer features a CNN Stem module integrated to preserve low-level and high-resolution features, enhancing the model’s capability to process details of aerial imagery. The proposed AerialFormer is designed with a hierarchical structure, in which a Transformer encoder generates multi-scale features and a multi-dilated CNN (MDC) decoder aggregates the information from the multi-scale inputs. As a result, information is taken into account in both local and global contexts, so that powerful representations and high-resolution segmentation can be achieved. The proposed AerialFormer was benchmarked on three benchmark datasets, including iSAID, LoveDA, and Potsdam. Comprehensive experiments and extensive ablation studies show that the proposed AerialFormer remarkably outperforms state-of-the-art methods.  more » « less
Award ID(s):
2345176
PAR ID:
10556613
Author(s) / Creator(s):
; ; ; ; ; ; ; ;
Publisher / Repository:
MDPI
Date Published:
Journal Name:
Remote Sensing
Volume:
16
Issue:
16
ISSN:
2072-4292
Page Range / eLocation ID:
2930
Subject(s) / Keyword(s):
remote sensing semantic segmentation transformers dilated convolution
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; (, PMLR)
    Vision graph neural networks (ViG) have demonstrated promise in vision tasks as a competitive alternative to conventional convolutional neural nets (CNN) and transformers (ViTs); however, common graph construction methods, such as k-nearest neighbor (KNN), can be expensive on larger images. While methods such as Sparse Vision Graph Attention (SVGA) have shown promise, SVGA’s fixed step scale can lead to over-squashing and missing multiple connections to gain the same information that could be gained from a long-range link. Through this observation, we propose a new graph construction method, Logarithmic Scalable Graph Construction (LSGC) to enhance performance by limiting the number of long-range links. To this end, we propose LogViG, a novel hybrid CNN-GNN model that utilizes LSGC. Furthermore, inspired by the successes of multiscale and high-resolution architectures, we introduce and apply a high-resolution branch and fuse features between our high-resolution and low-resolution branches for a multi-scale high-resolution Vision GNN network. Extensive experiments show that LogViG beats existing ViG, CNN, and ViT architectures in terms of accuracy, GMACs, and parameters on image classification and semantic segmentation tasks. Our smallest model, Ti-LogViG, achieves an average top-1 accuracy on ImageNet-1K of 79.9% with a standard deviation of ± 0.2%, 1.7% higher average accuracy than Vision GNN with a 24.3% reduction in parameters and 35.3% reduction in GMACs. Our work shows that leveraging long-range links in graph construction for ViGs through our proposed LSGC can exceed the performance of current state-of-the-art ViGs. 
    more » « less
  2. ; ; ; (, SPIE 11392, Algorithms, Technologies, and Applications for Multispectral and Hyperspectral Imagery XXVI)
    Messinger, David W.; Velez-Reyes, Miguel (Ed.)
    Recently, multispectral and hyperspectral data fusion models based on deep learning have been proposed to generate images with a high spatial and spectral resolution. The general objective is to obtain images that improve spatial resolution while preserving high spectral content. In this work, two deep learning data fusion techniques are characterized in terms of classification accuracy. These methods fuse a high spatial resolution multispectral image with a lower spatial resolution hyperspectral image to generate a high spatial-spectral hyperspectral image. The first model is based on a multi-scale long short-term memory (LSTM) network. The LSTM approach performs the fusion using a multiple step process that transitions from low to high spatial resolution using an intermediate step capable of reducing spatial information loss while preserving spectral content. The second fusion model is based on a convolutional neural network (CNN) data fusion approach. We present fused images using four multi-source datasets with different spatial and spectral resolutions. Both models provide fused images with increased spatial resolution from 8m to 1m. The obtained fused images using the two models are evaluated in terms of classification accuracy on several classifiers: Minimum Distance, Support Vector Machines, Class-Dependent Sparse Representation and CNN classification. The classification results show better performance in both overall and average accuracy for the images generated with the multi-scale LSTM fusion over the CNN fusion 
    more » « less
  3. ; ; ; ; ; (, Applied Sciences)
    Road extraction is a sub-domain of remote sensing applications; it is a subject of extensive and ongoing research. The procedure of automatically extracting roads from satellite imagery encounters significant challenges due to the multi-scale and diverse structures of roads; improvement in this field is needed. Convolutional neural networks (CNNs), especially the DeepLab series known for its proficiency in semantic segmentation due to its efficiency in interpreting multi-scale objects’ features, address some of these challenges caused by the varying nature of roads. The present work proposes the utilization of DeepLabV3+, the latest version of the DeepLab series, by introducing an innovative Dense Depthwise Dilated Separable Spatial Pyramid Pooling (DenseDDSSPP) module and integrating it in the place of the conventional Atrous Spatial Pyramid Pooling (ASPP) module. This modification enhances the extraction of complex road structures from satellite images. This study hypothesizes that the integration of DenseDDSSPP with a CNN backbone network and a Squeeze-and-Excitation block will generate an efficient dense feature map by focusing on relevant features, leading to more precise and accurate road extraction from remote sensing images. The Results Section presents a comparison of our model’s performance against state-of-the-art models, demonstrating better results that highlight the effectiveness and success of the proposed approach. 
    more » « less
  4. ; ; ; (, British Machine Vision Conference 2019)
    null (Ed.)
    Convolutional Neural Network (CNN) based image segmentation has made great progress in recent years. However, video object segmentation remains a challenging task due to its high computational complexity. Most of the previous methods employ a two-stream CNN framework to handle spatial and motion features separately. In this paper, we propose an end-to-end encoder-decoder style 3D CNN to aggregate spatial and temporal information simultaneously for video object segmentation. To efficiently process video, we propose 3D separable convolution for the pyramid pooling module and decoder, which dramatically reduces the number of operations while maintaining the performance. Moreover, we also extend our framework to video action segmentation by adding an extra classifier to predict the action label for actors in videos. Extensive experiments on several video datasets demonstrate the superior performance of the proposed approach for action and object segmentation compared to the state-of-the-art. 
    more » « less
  5. ; ; (, IEEE)
    Vision transformers (ViTs) have dominated computer vision in recent years. However, ViTs are computationally expensive and not well suited for mobile devices; this led to the prevalence of convolutional neural network (CNN) and ViT-based hybrid models for mobile vision applications. Recently, Vision GNN (ViG) and CNN hybrid models have also been proposed for mobile vision tasks. However, all of these methods remain slower compared to pure CNN-based models. In this work, we propose Multi-Level Dilated Convolutions to devise a purely CNN-based mobile backbone. Using Multi-Level Dilated Convolutions allows for a larger theoretical receptive field than standard convolutions. Different levels of dilation also allow for interactions between the short-range and long-range features in an image. Experiments show that our proposed model outperforms state-of-the-art (SOTA) mobile CNN, ViT, ViG, and hybrid architectures in terms of accuracy and/or speed on image classification, object detection, instance segmentation, and semantic segmentation. Our fastest model, RapidNet-Ti, achieves 76.3% top-1 accuracy on ImageNet-1K with 0.9 ms inference latency on an iPhone 13 mini NPU, which is faster and more accurate than MobileNetV2x1.4 (74.7% top-1 with 1.0 ms latency). Our work shows that pure CNN architectures can beat SOTA hybrid and ViT models in terms of accuracy and speed when designed properly 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email