Image segmentation has made great progress in recent years, but the annotation required for image segmentation is usually expensive, especially for remote sensing images. To solve this problem, we explore semi-supervised learning methods and appropriately utilize a large amount of unlabeled data to improve the performance of remote sensing image segmentation. This paper proposes a method for remote sensing image segmentation based on semi-supervised learning. We first design a Consistency Regularization (CR) training method for semi-supervised training, then employ the new learned model for Average Update of Pseudo-label (AUP), and finally combine pseudo labels and strong labels to train semantic segmentation network. We demonstrate the effectiveness of the proposed method on three remote sensing datasets, achieving better performance without more labeled data. Extensive experiments show that our semi-supervised method can learn the latent information from the unlabeled data to improve the segmentation performance.

Partner’s digital transformation is one of the most important metrics for businesses, particularly for businesses in the subscription world. Hence, how to predict partner transformation is a consistent focus in the industry. In this paper, we use an AI (Artificial Intelligence) relevant algorithm to analyze partner’s digital transformation issues and propose a novel method, named the hybrid VKR (VAE, K-means, and random forest) algorithm, to predict partner transformation. We apply our algorithm to partner transformation issues. First, we show the prediction of about 5980 partners from 25,689 partners, who are transformed and sorted according to important indicators. Secondly, we recap the tremendous effort that was required by the company to obtain high-quality results for economic change when a partner is transforming along with one or many of the transformation dimensions. Finally, we identify unethical behavior by looking through deal transaction data. Overall, our work sheds light on several potential problems in partner transformation and calls for improved scientific practices in this area.

Recommender systems face fundamental challenges, including extreme data sparsity and noisy rating observations. We propose L21RSVD, a robust latent factor model that employs L21 norm regularization within a Singular Value Decomposition framework to mitigate the impact of outliers while preserving low-rank structure. Unlike conventional L2-regularized approaches, our formulation induces group sparsity in the latent factor space, yielding more discriminative user and item representations. We derive three optimization variants: standard L21RSVD, L21RSVD without the squared term, and coefficient-free adaptive L21RSVD. Building upon these, we introduce a fusion strategy that adaptively aggregates predictions based on local data density. Extensive experiments on benchmark datasets demonstrate that L21RSVD substantially outperforms classical collaborative filtering and the SVD-type model. The proposed fusion model achieves state-of-the-art performance, reducing RMSE by up to 31.21% and MAE by up to 42.99% relative to baseline methods.