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

Zhang, Jun; Liu, Yue; Wu, Pengfei; Shi, Zhenwei; Pan, Bin

doi:10.3390/rs14051227

Cited by 6 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furtherly, segmentation that is based on deep learning methods relies on big data training [11,12], but remote sensing images are densely annotated and laborious to acquire. The studies in [13][14][15][16][17] explore how to reduce the need for dense annotation from self-/semi-supervised learning and weakly supervised learning. Jiang et al [18] introduced a few-shot learning method for remote sensing image segmentation.…”

Section: Few-shot Segmentation Of Remote Sensing Imagesmentioning

confidence: 99%

Semi-Supervised Contrastive Learning for Few-Shot Segmentation of Remote Sensing Images

et al. 2022

View full text Add to dashboard Cite

Deep learning has been widely used in remote sensing image segmentation, while a lack of training data remains a significant issue. The few-shot segmentation of remote sensing images refers to the segmenting of novel classes with a few annotated samples. Although the few-shot segmentation of remote sensing images method based on meta-learning can get rid of the dependence on large data training, the generalization ability of the model is still low. This work presents a few-shot segmentation of remote sensing images with a self-supervised background learner to boost the generalization capacity for unseen categories to handle this challenge. The methodology in this paper is divided into two main modules: a meta learner and a background learner. The background learner supervises the feature extractor to learning latent categories in the image background. The meta learner expands on the classic metric learning framework by optimizing feature representation through contrastive learning between target classes and latent classes acquired from the background learner. Experiments on the Vaihingen dataset and the Zurich Summer dataset show that our model has satisfactory in-domain and cross-domain transferring abilities. In addition, broad experimental evaluations on PASCAL-5i and COCO-20i demonstrate that our model outperforms the prior works of few-shot segmentation. Our approach surpassed previous methods by 1.1% with ResNet-101 in a 1-way 5-shot setting.

show abstract

Section: Few-shot Segmentation Of Remote Sensing Imagesmentioning

confidence: 99%

Semi-Supervised Contrastive Learning for Few-Shot Segmentation of Remote Sensing Images

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In contrast to other methods that only use image-level labels, this method introduces point-level labels as supervision to provide the location information of objects; however, these point-level labels require additional costs. CDSA [39] uses image-level labels to obtain location maps and provides structural information through the source domain. The structural information of the source domain can solve the problem of CAM over-activation.…”

Section: Weakly Supervised Semantic Segmentation Of Remote Sensing Im...mentioning

confidence: 99%

Reliable Label-Supervised Pixel Attention Mechanism for Weakly Supervised Building Segmentation in UAV Imagery

Peng

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Building segmentation for Unmanned Aerial Vehicle (UAV) imagery usually requires pixel-level labels, which are time-consuming and expensive to collect. Weakly supervised semantic segmentation methods for image-level labeling have recently achieved promising performance in natural scenes, but there have been few studies on UAV remote sensing imagery. In this paper, we propose a reliable label-supervised pixel attention mechanism for building segmentation in UAV imagery. Our method is based on the class activation map. However, classification networks tend to capture discriminative parts of the object and are insensitive to over-activation; therefore, class activation maps cannot directly guide segmentation network training. To overcome these challenges, we first design a Pixel Attention Module that captures rich contextual relationships, which can further mine more discriminative regions, in order to obtain a modified class activation map. Then, we use the initial seeds generated by the classification network to synthesize reliable labels. Finally, we design a reliable label loss, which is defined as the sum of the pixel-level differences between the reliable labels and the modified class activation map. Notably, the reliable label loss can handle over-activation. The preceding steps can significantly improve the quality of the pseudo-labels. Experiments on our home-made UAV data set indicate that our method can achieve 88.8% mIoU on the test set, outperforming previous state-of-the-art weakly supervised methods.

show abstract

“…As for remote sensing, it is time-consuming to obtain numerous annotated data. Therefore, some works [28][29][30] have aimed to reduce the need for annotations or use semi-supervised methods [31] to handle unknown categories.…”

Section: Introductionmentioning

confidence: 99%

Learn to Few-Shot Segment Remote Sensing Images from Irrelevant Data

Sun,

Chao,

Lin

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Few-shot semantic segmentation (FSS) is committed to segmenting new classes with only a few labels. Generally, FSS assumes that base classes and novel classes belong to the same domain, which limits FSS’s application in a wide range of areas. In particular, since annotation is time-consuming, it is not cost-effective to process remote sensing images using FSS. To address this issue, we designed a feature transformation network (FTNet) for learning to few-shot segment remote sensing images from irrelevant data (FSS-RSI). The main idea is to train networks on irrelevant, already labeled data but inference on remote sensing images. In other words, the training and testing data neither belong to the same domain nor category. The FTNet contains two main modules: a feature transformation module (FTM) and a hierarchical transformer module (HTM). Among them, the FTM transforms features into a domain-agnostic high-level anchor, and the HTM hierarchically enhances matching between support and query features. Moreover, to promote the development of FSS-RSI, we established a new benchmark, which other researchers may use. Our experiments demonstrate that our model outperforms the cutting-edge few-shot semantic segmentation method by 25.39% and 21.31% in the one-shot and five-shot settings, respectively.

show abstract

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

Cited by 6 publications

References 44 publications

Semi-Supervised Contrastive Learning for Few-Shot Segmentation of Remote Sensing Images

Semi-Supervised Contrastive Learning for Few-Shot Segmentation of Remote Sensing Images

Reliable Label-Supervised Pixel Attention Mechanism for Weakly Supervised Building Segmentation in UAV Imagery

Learn to Few-Shot Segment Remote Sensing Images from Irrelevant Data

Contact Info

Product

Resources

About