Hierarchical Weakly Supervised Learning for Residential Area Semantic Segmentation in Remote Sensing Images

Zhang, Libao; Ma, Jie; Lv, Xinran; Chen, Donghui

doi:10.1109/lgrs.2019.2914490

Cited by 46 publications

(17 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A global convolutional pooling operation and a local pooling pruning strategy were introduced into a WSSS framework to address cloud detection [55]. Hierarchical residual saliency maps combined with superpixel were generated to fulfill residential-area segmentation with a novel hierarchical weakly supervised learning method [56]. A weakly supervised feature-fusion network was proposed to accomplish water and cloud segmentation in RS images [57].…”

Section: Wsss Methods On Rs Imagerymentioning

confidence: 99%

Improved Pseudomasks Generation for Weakly Supervised Building Extraction From High-Resolution Remote Sensing Imagery

Fang

Zheng

et al. 2022

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

View full text Add to dashboard Cite

Benefiting from free labeling pixel-level samples, weakly supervised semantic segmentation (WSSS) is making progress in automatically extracting building from high-resolution (HR) remote sensing (RS) imagery. For WSSS methods, generating high-quality pseudo-masks is crucial for accurate building extraction. To improve the performance of generating pseudo-masks by using imagelevel labels, this paper proposes a weakly supervised building extraction method by combining adversarial climbing and gated convolution (ACGC). The proposed method optimizes class activation maps (CAMs) by using adversarial climbing strategy, generates accurate class boundary maps (CBMs) by introducing a gated convolution module (GCM), and further refines building pseudo-masks by fusing pairing semantic affinities and CAMs with a random walk strategy. Experimental results on three datasets-two ISPRS datasets and a self-annotated dataset-demonstrate that the proposed approach outperformed SOTA WSSS methods, leading to improvement of building extraction from HR RS imagery.This study provides a new approach for optimizing pseudomasks generation, and a methodological reference for the applications of weakly supervised on RS images.

show abstract

Section: Wsss Methods On Rs Imagerymentioning

confidence: 99%

Improved Pseudomasks Generation for Weakly Supervised Building Extraction From High-Resolution Remote Sensing Imagery

Fang

Zheng

et al. 2022

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

View full text Add to dashboard Cite

show abstract

“…A novel weakly supervised network was proposed to extract roads from very high-resolution images [30]. Zhang et al [31] integrated class-specific multiscale salient features implement residential area segmentation under weak supervision. Although the aforementioned methods have achieved significant improvement under weakly supervised learning, they ignored the structure information of objects, which would not be applicable to the building segmentation from remote sensing.…”

Section: Weakly Supervised Learningmentioning

confidence: 99%

Mining Cross-Domain Structure Affinity for Refined Building Segmentation in Weakly Supervised Constraints

Zhang

Liu

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Building segmentation for remote sensing images usually requires pixel-level labels which is difficult to collect when the images are in low resolution and quality. Recently, weakly supervised semantic segmentation methods have achieved promising performance, which only rely on image-level labels for each image. However, buildings in remote sensing images tend to present regular structures. The lack of supervision information may result in the ambiguous boundaries. In this paper, we propose a new weakly supervised network for refined building segmentation by mining the cross-domain structure affinity (CDSA) from multi-source remote sensing images. CDSA integrates the ideas of weak supervision and domain adaptation, where a pixel-level labeled source domain and an image-level labeled target domain are required. The target of CDSA is to learn a powerful segmentation network on the target domain with the guidance of source domain data. CDSA mainly consists of two branches, the structure affinity module (SAM) and the spatial structure adaptation (SSA). In brief, SAM is developed to learn the structure affinity of the buildings from source domain, and SSA infuses the structure affinity to the target domain via a domain adaptation approach. Moreover, we design an end-to-end network structure to simultaneously optimize the SAM and SSA. In this case, SAM can receive pseudosupervised information from SSA, and in turn provide a more accurate affinity matrix for SSA. In the experiments, our model can achieve an IoU score at 57.87% and 79.57% for the WHU and Vaihingen data sets. We compare CDSA with several state-of-the-art weakly supervised and domain adaptation methods, and the results indicate that our method presents advantages on two public data sets.

show abstract

“…Segmentation techniques are categorized into two types: similarity-based and discontinuity-based segmentation. Segmentation plays a key role in almost all areas such as image retrieval, object identification, medical image processing [6,7], image de-noising, and remote sensing image processing [8,9]. Recently, deep learning [10,11] and constrained based image segmentation were proposed for improving image segmentation [12].…”

Section: Introductionmentioning

confidence: 99%

Image Segmentation Based on Block Level and Hybrid Directional Local Extrema

Raghuwanshi¹,

Gupta²,

Sinwar³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

In the recent decade, the digitalization of various tasks has added great flexibility to human lifestyle and has changed daily routine activities of communities. Image segmentation is a key step in digitalization. Segmentation plays a key role in almost all areas of image processing, and various approaches have been proposed for image segmentation. In this paper, a novel approach is proposed for image segmentation using a nonuniform adaptive strategy. Region-based image segmentation along with a directional binary pattern generated a better segmented image. An adaptive mask of 8 × 8 was circulated over the pixels whose bit value was 1 in the generated directional binary pattern. Segmentation was performed in three phases: first, an image was divided into sub-images or image chunks; next, the image patches were taken as input, and an adaptive threshold was generated; and finally the image chunks were processed separately by convolving the adaptive mask on the image chunks. Gradient and Laplacian of Gaussian algorithms along with directional extrema patterns provided a double check for boundary pixels. The proposed approach was tested on chunks of varying sizes, and after multiple iterations, it was found that a block size of 8 × 8 performs better than other chunks or block sizes. The accuracy of the segmentation technique was measured in terms of the count of ill regions, which were extracted after the segmentation process.

show abstract

Hierarchical Weakly Supervised Learning for Residential Area Semantic Segmentation in Remote Sensing Images

Cited by 46 publications

References 9 publications

Improved Pseudomasks Generation for Weakly Supervised Building Extraction From High-Resolution Remote Sensing Imagery

Improved Pseudomasks Generation for Weakly Supervised Building Extraction From High-Resolution Remote Sensing Imagery

Mining Cross-Domain Structure Affinity for Refined Building Segmentation in Weakly Supervised Constraints

Image Segmentation Based on Block Level and Hybrid Directional Local Extrema

Contact Info

Product

Resources

About