Building Change Detection for VHR Remote Sensing Images via Local–Global Pyramid Network and Cross-Task Transfer Learning Strategy

Liu, Tongfei; Gong, Maoguo; Lu, Di; Zhang, Qingfu; Zheng, Hanhong; Jiang, Fenlong; Zhang, Mingyang

doi:10.1109/tgrs.2021.3130940

Cited by 54 publications

(24 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite a large amount of RS data, high-quality labels via manual annotation could be costly. Many efforts in RS CD have been made to tackle the label insufficiency, including applying data augmentation [37][38][39][40][41][42][43], generating pseudo labels for unlabeled data via semisupervised learning [36,44,45], using active learning to select a small number of informative samples [46][47][48][49], and finetuning a pre-trained model [8,10,16,17,19,50,51].…”

Section: A Handling Label Insufficiency In CDmentioning

confidence: 99%

“…Data augmentation is an effective solution to enhance the size of the training dataset. The most common way is to use transformation-based augmentations [37,[39][40][41][42][43], including geometric transformations (e.g., random crop, horizontal flip), color transformations, and Gaussian blur, etc. A recent advance increases the number of the positive samples (change of interest) by blending the gan-generated instance on the appropriate spatial-temporal position of the bitemporal image [38].…”

Section: A Handling Label Insufficiency In CDmentioning

confidence: 99%

See 1 more Smart Citation

Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection

Chen,

Li,

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

Training deep learning-based change detection (CD) model heavily depends on labeled data. Contemporary transfer learning-based methods to alleviate the CD label insufficiency mainly upon ImageNet pre-training. A recent trend is using remote sensing (RS) data to obtain in-domain representations via supervised or self-supervised learning (SSL). Here, different from traditional supervised pre-training that learns the mapping from image to label, we leverage semantic supervision in a contrastive manner. There are typically multiple objects of interest (e.g., buildings) distributed in varying locations in RS images. We propose dense semantic-aware pre-training for RS image CD via sampling multiple class-balanced points. Instead of manipulating image-level representations that lack spatial information, we constrain pixel-level cross-view consistency and cross-semantic discrimination to learn spatially-sensitive features, thus benefiting downstream dense CD. Apart from learning illumination invariant features, we fulfill consistent foreground features insensitive to irrelevant background changes via a synthetic view using background swapping. We additionally achieve discriminative representations to distinguish foreground land-covers and other backgrounds. We collect large-scale image-mask pairs freely available in the RS community for pre-training. Extensive experiments on three CD datasets verify the effectiveness of our method. Ours significantly outperforms ImageNet, in-domain supervision, and several SSL methods. Empirical results indicate ours well alleviates data insufficiency in CD. Notably, we achieve competitive results using only 20% training data than random baseline using 100% data. Both quantitative and qualitative results demonstrate the generalization ability of our pre-trained model to downstream images even remaining domain gaps with the pre-training data. Our data and code will make public.

show abstract

Section: A Handling Label Insufficiency In CDmentioning

confidence: 99%

Section: A Handling Label Insufficiency In CDmentioning

confidence: 99%

Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection

Chen,

Li,

Chen

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…With the advancement of remote sensing technology, more and more abundant ground information can be obtained from remote sensing images, which facilitates many research directions and applications, such as change detection [1][2][3][4][5][6], land use classification [7,8], remote sensing image classification [9,10], etc. As a basic task of remote sensing image processing [11], remote sensing image classification is the classification of remote sensing scene images into a group of semantic categories, which has been widely used in environmental monitoring [12], geospatial object detection [13], and urban planning [14].…”

Section: Introductionmentioning

confidence: 99%

TPENAS: A Two-Phase Evolutionary Neural Architecture Search for Remote Sensing Image Classification

Feng

Sheng

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

The application of deep learning in remote sensing image classification has been paid more and more attention by industry and academia. However, manually designed remote sensing image classification models based on convolutional neural networks usually require sophisticated expert knowledge. Moreover, it is notoriously difficult to design a model with both high classification accuracy and few parameters. Recently, neural architecture search (NAS) has emerged as an effective method that can greatly reduce the heavy burden of manually designing models. However, it remains a challenge to search for a classification model with high classification accuracy and few parameters in the huge search space. To tackle this challenge, we propose TPENAS, a two-phase evolutionary neural architecture search framework, which optimizes the model using computational intelligence techniques in two search phases. In the first search phase, TPENAS searches for the optimal depth of the model. In the second search phase, TPENAS searches for the structure of the model from the perspective of the whole model. Experiments on three open benchmark datasets demonstrate that our proposed TPENAS outperforms the state-of-the-art baselines in both classification accuracy and reducing parameters.

show abstract

“…Especially in agriculture, change detection is often used for arable land area control, plantation monitoring, disaster assessment [17], deforestation monitoring, forest resource control, etc. For urban areas, building change monitoring [18] is also a helpful task. It is of great interest in applications such as urban environment, town expansion monitoring, urban development planning, and assessment of natural disasters like earthquakes [19].…”

Section: Introductionmentioning

confidence: 99%

SSCFNet: A Spatial-Spectral Cross Fusion Network for Remote Sensing Change Detection

Wang

Liu

Jiao

et al. 2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Convolutional Neural Networks(CNNs) are datadriven methods that automatically extract the rich information embedded in remote sensing images. However, most current deep learning-based remote sensing image change detection methods prioritize high-level semantic features, while not enough attention is given to low-level semantic features, resulting in the loss of edges and details of the change region. To address this problem, this paper constructs a spatial-spectral cross fusion network SSCFNet, divided into three modules: a feature extractor network module, a combined enhancement module, and a semantic cross-fusion module. A new combined enhancement strategy is proposed to construct several semantic feature blocks in the combined enhancement module. Different convolution operations are applied to the newly constructed semantic feature blocks in the semantic cross fusion module, and the obtained semantic features at various levels are cross-fused. Experiments show that the proposed SSCFNet outperforms the other six state-of-the-art methods on four publicly available remote sensing image change detection datasets.

show abstract

Building Change Detection for VHR Remote Sensing Images via Local–Global Pyramid Network and Cross-Task Transfer Learning Strategy

Cited by 54 publications

References 64 publications

Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection

Semantic-aware Dense Representation Learning for Remote Sensing Image Change Detection

TPENAS: A Two-Phase Evolutionary Neural Architecture Search for Remote Sensing Image Classification

SSCFNet: A Spatial-Spectral Cross Fusion Network for Remote Sensing Change Detection

Contact Info

Product

Resources

About