Scene Classification With Recurrent Attention of VHR Remote Sensing Images

By Qi Wang, Shaoteng Liu, Jocelyn Chanussot, Xuelong Li. IEEE Transactions on Geoscience and Remote Sensing, 2019

511 citations recorded by the source corpus.

Scene classification of remote sensing images has drawn great attention because of its wide applications. In this paper, with the guidance of the human visual system (HVS), we explore the attention mechanism and propose a novel end-to-end attention recurrent convolutional network (ARCNet) for scene classification. It can learn to focus selectively on some key regions or locations and just process them at high-level features, thereby discarding the noncritical information and promoting the classification performance. The contributions of this paper are threefold. First, we design a novel recurrent attention structure to squeeze high-level semantic and spatial features into several simplex vectors for the reduction of learning parameters. Second, an end-to-end network named ARCNet is proposed to adaptively select a series of attention regions and then to generate powerful predictions by learning to process them sequentially. Third, we construct a new data set named OPTIMAL-31, which contains more categories than popular data sets and gives researchers an extra platform to validate their algorithms. The experimental results demonstrate that our model makes great promotion in comparison with the state-of-the-art approaches.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/57dcc8c82b46fc2766346bf03ab44342a8ae0bcb

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Classification of Remote Sensing Images Using EfficientNet-B3 CNN Model With Attention (2021, methodology): “the RSSCN7 dataset [10], the OPTMIAL-31 dataset [40], the WHU-RS19 dataset [15], and the last and largest one is the Aerial Image Datasets (AID) dataset [59].”
A Contrastive Continual Learning for the Classification of Remote Sensing Imagery (2022, background): “The broad subject of remote sensing involves many different data types such as normal 2D image, very high-resolution image (VHR) [1], hyperspectral image (HSI) [2].”
RemoteCLIP: A Vision Language Foundation Model for Remote Sensing (2023, unknown): “We used a total of 12 downstream datasets, including PatternNet [97], EuroSAT [98], OPTIMAL-31 [99], RSC11 [100], AID [101], MLRSNet [102], RSI-CB128 [103], RSI-CB256 [103], RESISC45 [104], WHU-earth [105], WHU-RS19 [106], and RS2800 [107].”
Transformers in Remote Sensing: A Survey (2022, methodology): “Optimal31 [77], NWPU [78] Overall classification accuracy Integrates transformers into CNNs by replacing the last three ResNet bottlenecks with encoders having multi-head self-attention bottleneck.”
Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities (2020, background): “4& 6 [126], RSSCN7 [125], Brazilian Coffee Scene [85], RSC11 [128], SIRI-WHU [127], RSCI-CB [129], AID [79], NWPU-RESISC45 [80], OPTIMAL-31 [74], EuroSAT [130],”
Continual Learning Using Data Regeneration for Remote Sensing Scene Classification (2022, methodology): “The third method, proposed in [18], fights the forgetting phenomenon by selectively reducing learning on the weights that are important for performed tasks.”
Continual Learning Approach for Remote Sensing Scene Classification (2020, methodology): “The Merced data set was captured from the United States Geographical Survey (USGS) National Map [13].”
RSVQA: Visual Question Answering for Remote Sensing Data (2020, background): “More recently, [11] used an intermediate high-level representation using recurrent attention maps to classify images.”
Vision Transformers for Remote Sensing Image Classification (2021, methodology): “In our experiments, three well-known remote-sensing datasets are used for evaluation: Merced land-use dataset [57], Aerial image dataset (AID) [58], and the Optimal-31 [41] dataset.”
Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning (2022, methodology): “Our analysis uses eight different land-use classification datasets: RESISC-45 [11], the UC Merced Land Use Dataset [65], AiRound and CV-BrCT [43], MLRSNet [48], EuroSAT [29], Optimal-31 [55], WHU-RS19 [14], SpaceNet v1 and v2 [53], and Functional Map of the World [12].”
CAD-Net: A Context-Aware Detection Network for Objects in Remote Sensing Imagery (2019, methodology): “techniques for remote sensing scene classification, [45] further adopts a recurrent attention structure to effectively search for”