Style Transformation-Based Change Detection Using Adversarial Learning with Object Boundary Constraints

Zhang, Xiaokang; Yu, Weikang; Pun, Man-On; Ming, Liu

doi:10.1109/igarss47720.2021.9554645

Cited by 3 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to address the task of CD from multi-temporal imagery with domain shift (such as seasonal differences and style differences), a transformer-driven image translation module is proposed to map data between two images with real-time efficiency. Unlike GAN-based image-to-image translation [28], [31], [36], transformer-driven image translation adopts the expressive multi-head attention strategy from the well-known transformer architecture [47] to globally model a new image, whose image content is coherent with the pre-change image, and whose style is optionally the same as the post-change image. As Fig.…”

Section: Methodology a Transformer-driven Image Translationmentioning

confidence: 99%

“…1) Building effective representation of multi-temporal images at the pixel-level [28], [31], [32], feature-level [29], [33], [34], or object-level [35], [36]. Importantly, homogeneous data captured by the same types of sensors and heterogeneous images captured by different types of sensors use different methods to establish an effective representation of multitemporal images.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unsupervised Semantic-Based Aggregation of Deep Convolutional Features

Wang

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

In this paper, we propose a simple but effective semantic-based aggregation (SBA) method. The proposed SBA utilizes the discriminative filters of deep convolutional layers as semantic detectors. Moreover, we propose the effective unsupervised strategy to select some semantic detectors to generate the "probabilistic proposals", which highlight certain discriminative pattern of objects and suppress the noise of background. The final global SBA representation could then be acquired by aggregating the regional representations weighted by the selected "probabilistic proposals" corresponding to various semantic content. Our unsupervised SBA is easy to generalize and achieves excellent performance on various tasks. We conduct comprehensive experiments and show that our unsupervised SBA outperforms the state-of-the-art unsupervised and supervised aggregation methods on image retrieval, place recognition and cloud classification.

show abstract

Section: Methodology a Transformer-driven Image Translationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Unsupervised Semantic-Based Aggregation of Deep Convolutional Features

Wang

et al. 2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

UCDFormer: Unsupervised Change Detection Using a Transformer-Driven Image Translation

Xu,

Shi,

Guo

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Change detection (CD) by comparing two bitemporal images is a crucial task in remote sensing. With the advantages of requiring no cumbersome labeled change information, unsupervised CD has attracted extensive attention in the community. However, existing unsupervised CD approaches rarely consider the seasonal and style differences incurred by the illumination and atmospheric conditions in multi-temporal images. To this end, we propose a change detection with domain shift setting for remote sensing images. Furthermore, we present a novel unsupervised CD method using a light-weight transformer, called UCDFormer. Specifically, a transformer-driven image translation composed of a light-weight transformer and a domain-specific affinity weight is first proposed to mitigate domain shift between two images with real-time efficiency. After image translation, we can generate the difference map between the translated before-event image and the original after-event image. Then, a novel reliable pixel extraction module is proposed to select significantly changed/unchanged pixel positions by fusing the pseudo change maps of fuzzy c-means clustering and adaptive threshold. Finally, a binary change map is obtained based on these selected pixel pairs and a binary classifier. Experimental results on different unsupervised CD tasks with seasonal and style changes demonstrate the effectiveness of the proposed UCDFormer. For example, compared with several other related methods, UCDFormer improves performance on the Kappa coefficient by more than 12%. In addition, UCDFormer achieves excellent performance for earthquake-induced landslide detection when considering large-scale applications. The code is available at https://github.com/zhu-xlab/UCDFormer.

show abstract

Adaptive convolution kernel network for change detection in hyperspectral images

Liu

Chen

et al. 2023

Appl. Opt.

View full text Add to dashboard Cite

Feature extraction is a key step in hyperspectral image change detection. However, many targets with great various sizes, such as narrow paths, wide rivers, and large tracts of cultivated land, can appear in a satellite remote sensing image at the same time, which will increase the difficulty of feature extraction. In addition, the phenomenon that the number of changed pixels is much less than unchanged pixels will lead to class imbalance and affect the accuracy of change detection. To address the above issues, based on the U-Net model, we propose an adaptive convolution kernel structure to replace the original convolution operations and design a weight loss function in the training stage. The adaptive convolution kernel contains two various kernel sizes and can automatically generate their corresponding weight feature map during training. Each output pixel obtains the corresponding convolution kernel combination according to the weight. This structure of automatically selecting the size of the convolution kernel can effectively adapt to different sizes of targets and extract multi-scale spatial features. The modified cross-entropy loss function solves the problem of class imbalance by increasing the weight of changed pixels. Study results on four datasets indicate that the proposed method performs better than most existing methods.

show abstract

Style Transformation-Based Change Detection Using Adversarial Learning with Object Boundary Constraints

Cited by 3 publications

References 3 publications

Unsupervised Semantic-Based Aggregation of Deep Convolutional Features

Unsupervised Semantic-Based Aggregation of Deep Convolutional Features

UCDFormer: Unsupervised Change Detection Using a Transformer-Driven Image Translation

Adaptive convolution kernel network for change detection in hyperspectral images

Contact Info

Product

Resources

About