Semi-Supervised Semantic Segmentation of Remote Sensing Images With Iterative Contrastive Network

Wang, Jia-Xin; Chen, Si‐Bao; Ding, Chris; Tang, Jin; Luo, Bin

doi:10.1109/lgrs.2022.3157032

Cited by 24 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the proposed method's performance, we make comparisons with several popular semi-supervised methods on dam-water and building datasets, such as Paste Consistency (RanPaste) 14 , Pixel-Level SSL (PL-SSL) 15 , CCT, DCT, and Iterative Contrastive Network (ICNet) 16 . The comparison results are shown in Table 2.…”

Section: Comparison Resultsmentioning

confidence: 99%

A semi-supervised network for object segmentation of remote sensing images

Zhang,

Liu,

Mou

et al. 2024

MIPPR 2023: Automatic Target Recognition and Navigation

View full text Add to dashboard Cite

Recently, object segmentation of remote sensing images has achieved great progress in many fields, such as transportation, natural resource, ecology, et al. A lot of works mainly performed object segmentation in fully-supervised mode. However, training models in such mode usually need craft large-scale annotations, which is usually an expensive work and costs much time. In this paper, a novel semi-supervised network for object segmentation of remote sensing images is proposed, which is only fed with a small amount of labeled data and relatively more unlabeled data. Rather than using the same architecture as previous semi-supervised works, we exploit two networks with different architectures, i.e. CNN and Transformer, as the cross-supervised models. Moreover, three types of loss functions, namely fully-supervised loss, cross-supervised loss and consistency loss, are introduced to enhance the model's robustness. The effectiveness of our proposed method is evaluated on two annotated remote sensing datasets, outperforming several state-of-the-art semi-supervised approaches.

show abstract

Section: Comparison Resultsmentioning

confidence: 99%

A semi-supervised network for object segmentation of remote sensing images

Zhang,

Liu,

Mou

et al. 2024

MIPPR 2023: Automatic Target Recognition and Navigation

View full text Add to dashboard Cite

show abstract

“…J.X. Wang et al presented an iterative contrastive network for remote sensing image semantic segmentation, which can continuously learn more potential information from labeled samples and generate better pseudo-labels for unlabeled data [34]. S. Desai et al employed active learning techniques to generate pseudo-labels from a small set of labeled examples which are used to augment the labeled training set, and enhanced the performance of remote sensing semantic segmentation network [35].…”

Section: Semi-supervised and Weakly Supervised Deep Learning Methodsmentioning

confidence: 99%

SW-GAN: Road Extraction from Remote Sensing Imagery Using Semi-Weakly Supervised Adversarial Learning

Chen

Peng

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Road networks play a fundamental role in our daily life. It is of importance to extract the road structure in a timely and precise manner with the rapid evolution of urban road structure. Recently, road network extraction using deep learning has become an effective and popular method. The main shortcoming of the road extraction using deep learning methods lies in the fact that there is a need for a large amount of training datasets. Additionally, the datasets need to be elaborately annotated, which is usually labor-intensive and time-consuming; thus, lots of weak annotations (such as the centerline from OpenStreetMap) have accumulated over the past a few decades. To make full use of the weak annotations, we propose a novel semi-weakly supervised method based on adversarial learning to extract road networks from remote sensing imagery. Our method uses a small set of pixel-wise annotated data and a large amount of weakly annotated data for training. The experimental results show that the proposed approach can achieve a maintained performance compared with the methods that use a large number of full pixel-wise annotations while using less fully annotated data.

show abstract

“…Zhang et al [7] performed Transformation Consistency Regularization on the prediction labels of the teacher network and compared the results with the student network, extending randomness to the label level. ICNet [17], during the training process, alternates between transforming the student network and the teacher network. This approach allows the two networks to supervise each other, thereby increasing perturbations at the network level.…”

Section: Semi-supervised Semantic Segmentation Of Aerial Imagerymentioning

confidence: 99%

“…Currently, the consistency regularization methods applied in the field of remote sensing are mostly extensions of methods from natural scenes. For instance, Zhang [7] applies various random transformations and perturbations to images and predicted labels; ICNet [17] switches between student and teacher networks based on training rounds, adding network perturbations. Although these methods have improved the results of the remote sensing dataset, they focus more on the image level and do not consider the feature level of the remote sensing images.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Semi-Supervised Semantic Segmentation of Remote Sensing Images via Feature Perturbation-Based Consistency Regularization Methods

Xin,

Fan,

et al. 2024

Sensors

View full text Add to dashboard Cite

In the field of remote sensing technology, the semantic segmentation of remote sensing images carries substantial importance. The creation of high-quality models for this task calls for an extensive collection of image data. However, the manual annotation of these images can be both time-consuming and labor-intensive. This has catalyzed the advent of semi-supervised semantic segmentation methodologies. Yet, the complexities inherent within the foreground categories of these remote sensing images present challenges in preserving prediction consistency. Moreover, remote sensing images possess more complex features, and different categories are confused within the feature space, making optimization based on the feature space challenging. To enhance model consistency and to optimize feature-based class categorization, this paper introduces a novel semi-supervised semantic segmentation framework based on Mean Teacher (MT). Unlike the conventional Mean Teacher that only introduces perturbations at the image level, we incorporate perturbations at the feature level. Simultaneously, to maintain consistency after feature perturbation, we employ contrastive learning for feature-level learning. In response to the complex feature space of remote sensing images, we utilize entropy threshold to assist contrastive learning, selecting feature key-values more precisely, thereby enhancing the accuracy of segmentation. Extensive experimental results on the ISPRS Potsdam dataset and the challenging iSAID dataset substantiate the superior performance of our proposed methodology.

show abstract

Semi-Supervised Semantic Segmentation of Remote Sensing Images With Iterative Contrastive Network

Cited by 24 publications

References 19 publications

A semi-supervised network for object segmentation of remote sensing images

A semi-supervised network for object segmentation of remote sensing images

SW-GAN: Road Extraction from Remote Sensing Imagery Using Semi-Weakly Supervised Adversarial Learning

Enhancing Semi-Supervised Semantic Segmentation of Remote Sensing Images via Feature Perturbation-Based Consistency Regularization Methods

Contact Info

Product

Resources

About