PICS: Paradigms Integration and Contrastive Selection for Semisupervised Remote Sensing Images Semantic Segmentation

Qi, Xiyu; Mao, Yiqi; Zhang, Yidan; Deng, Yawen; Wei, Haoran; Wang, Lei

doi:10.1109/tgrs.2023.3239042

Cited by 6 publications

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach allows the two networks to supervise each other, thereby increasing perturbations at the network level. PICS [5] adopts a selective self-training strategy. By using labelled images, it selects generated samples that are closer to the true values, thereby reducing the accumulation of potential errors.…”

Section: Semi-supervised Semantic Segmentation Of Aerial Imagerymentioning

confidence: 99%

“…The goal of semantic segmentation is to assign each pixel in the image to an interpretable category. At present, the semantic segmentation of remote sensing images has played a significant role in fields such as military reconnaissance [5], urban planning [6], and environmental monitoring [7], greatly facilitating the automation and decision optimization in these areas. However, due to the characteristics of remote sensing images, conducting pixel-level manual annotation is extremely laborious and time-consuming.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Semi-supervised Semantic Segmentation Of Aerial Imagerymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%