YWYuze Wang

Yuze Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuze Wang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Joint Learning for Feature Reconstruction and Prediction in Agricultural Semantic Segmentation From Incomplete Satellite Image Time Series

    by Yuze Wang, Mariana Belgiu, Haiyang Wu, Dandan Zhong, Yangyang Cao, Haifeng Li, Chao Tao

    Satellite Image Time Series (SITS) is crucial for semantic segmentation (SS) in agriculture applications. However, cloud contamination introduces time gaps in SITS, disrupting temporal dependencies and causing feature shifts, which decreases the performance of models pre-trained on complete SITS. Existing methods typically address this challenge by reconstructing the entire SITS before prediction or using data augmentation to simulate missing data. Yet, full reconstruction may introduce noise and redundancy, whereas the data augmentation model can only handle limited missing patterns, leading to poor generalization. We propose a joint learning framework with feature reconstruction and prediction to address incomplete SITS more effectively. Specifically, we simulate temporal missing scenarios using temporal masks. The two tasks are guided by both ground-truth labels and the teacher model trained on complete SITS. The prediction task constrains the model from selectively reconstructing temporal features, ensuring they align with the teacher’s complete representations and are beneficial for prediction. It reduces unnecessary reconstruction and limits noise propagation. By integrating reconstructed features into the prediction task, the model avoids learning shortcuts and maintains its ability to handle varied missing patterns and complete SITS. The experiments show strong generalization capabilities in multiple aspects: (1) Different SS tasks, including cropland extraction and crop classification; (2) Different study areas, including Hunan Province,Western France, and Catalonia; (3) Different sensors, primarily Sentinel-2 and PlanetScope; (4) Different numbers of time gaps, while retaining the model’s performance on complete SITS; (5) Different model architectures, including seven typical backbones. The source codes are available at: https://github.com/wangyuze-csu/Joint_FRP.

  • Weakly Supervised Framework Considering Multi-Temporal Information for Large-Scale Cropland Mapping With Satellite Imagery

    by Yuze Wang, Aoran Hu, Ji Qi, Yang Liu, Chao Tao

    Accurately mapping large-scale cropland is crucial for agricultural production management and planning. Currently, the combination of remote sensing data and deep learning techniques has shown outstanding performance in cropland mapping. However, those approaches require massive precise labels, which are labor-intensive. To reduce the label cost, this study presented a weakly supervised framework considering multi-temporal information for large-scale cropland mapping. Specifically, we extract high-quality labels according to their consistency among global land cover (GLC) products to construct the supervised learning signal. On the one hand, to alleviate the over-fitting problem caused by the model’s over-trust of remaining errors in high-quality labels, we encode the similarity/ aggregation of cropland in the visual/spatial domain to construct the unsupervised learning signal, and take it as the regularization term to constrain the supervised part. On the other hand, to sufficiently leverage the plentiful information in the samples without high-quality labels, we also incorporate the unsupervised learning signal in these samples, enriching the diversity of the feature space. After that, to capture the phenological features of croplands, we introduce dense satellite image time series (SITS) to extend the proposed framework in the temporal dimension. We also visualized the high-dimensional phenological features to uncover how multi-temporal information benefits cropland extraction, and assessed the method’s robustness under conditions of data scarcity. The proposed framework has been experimentally validated for strong adaptability across three study areas (Hunan Province, Southeast France, and Kansas) in large-scale cropland mapping, and the internal mechanism and temporal generalizability are also investigated. The source codes are available at https://github.com/wangyuze-csu/WSFCMI.


  • Top Cited Papers

    FSVLM: A Vision-Language Model for Remote Sensing Farmland Segmentation

    by Haiyang Wu, Zhuofei Du, Dandan Zhong, Yuze Wang, Chao Tao

    Existing visual deep learning paradigms, which are based on labels, struggle to capture the intricate interrelationships between farmland and its surrounding environment, and fail to account for temporal variations associated with the phenological cycle. These limitations lead to omissions and confusion in the recognition process, greatly impacting the accuracy and efficiency of farmland recognition. Language can accurately depict the spatial attributes of farmland, profoundly express the unique phenological landscapes of farmland that change with seasons and growth stages, and express the intricate interactions between these changes and environmental factors. This capability can address the deficiencies of label-based visual deep learning in understanding the complex features of farmland. This study explored, for the first time, the application of language-guided vision-language models (VLMs) for farmland segmentation. Firstly, as current VLM research lack dedicated farmland image text pair (FIT) dataset, this study constructed a FIT dataset by two steps. Step1, design a semi-automatic text description annotation framework for farmland images based on 12 key factors influencing farmland segmentation. Step2, use the framework to construct the FIT dataset. Then, a VLM for farmland segmentation (FSVLM) was designed by combining a semantic segmentation model with a multimodal large language model. Comparative experiments demonstrated that the proposed method outperforms existing farmland segmentation methods in both generalization and segmentation accuracy. In addition, a series of ablation experiments were conducted to examine the impacts of language descriptions of different semantic levels on the model's farmland information extraction performance.


  • Open Access

    A General Transitive Transfer Learning Framework for Cross-Optical Sensor Remote Sensing Image Scene Understanding

    by Chao Tao, Rong Xiao, Yuze Wang, Ji Qi, Haifeng Li

    During the past decades, the invention and employment of multiple sensors enable multi-sensor remote-sensing (RS) image acquisition. In order to effectively use these images for RS scene understanding, a scene classification model trained with samples collected from one sensor should generalize well to other sensors. However, it is extremely challenging to directly transfer between different sensors. The key reason is that: If we regard the images obtained by different sensors as the data distributed in different domains, there are large inter-domain gaps caused by multiple factors like image scene contents and sensor imaging parameters. To address this, we proposed a general Transitive Transfer Learning (TTL) framework for cross-optical sensor remote sensing image scene understanding, which can be easily coupled with most of the existing transfer learning methods. The core idea is to gradually minimize the inter-domain gap between different sensors by a set of intermediate domains, which are constructed by a single-factor criterion that only one factor is changed between adjacent domains. Then one challenging cross-optical sensor scene understanding task can be devided into several easier sub-tasks connected by these intermediate domains (source domain $\rightarrow 1^{st}$ intermediate domain $\rightarrow 2^{nd}$ intermediate domain $\rightarrow \dots \rightarrow$ target domain). Each sub-task can be regarded as a direct-transfer task, and can be completed using a mainstream transfer learning method. Experiments using six sets of cross-optical sensor RSIs datasets demonstrated that the framework can fit most transfer learning methods and improve their performance. Our framework achieve a new state-of-the-art compared to recently published transfer learning methods.


  • Cross-Sensor Remote-Sensing Images Scene Understanding Based on Transfer Learning Between Heterogeneous Networks

    by Yuze Wang, Rong Xiao, Ji Qi, Chao Tao

    Over the past decades, the successful invention and employment of multiple sensors have marked the advent of a new era in multisensor remote-sensing (RS) images acquisition. To effectively utilize the massive multisensor images for RS scene understanding, we expect that a scene classification model learned with particular sensor data can generalize well to other sensor data. However, this is a very challenging task due to the cross-sensor data differences. In the deep learning (DL) pipeline, a common way to handle this challenging task is to fine-tune the models pretrained on source sensor data with limited labeled data from the target sensor. Unfortunately, fine-tune technique is usually applied between homogeneous networks, which may not be the best choice if the source and target data are largely different. To address these issues, we formulate the cross-sensor RS scene understanding problem as a heterogeneous network-oriented transfer learning problem, in which the source and the target networks are different and data-oriented selected. Afterward, the knowledge between heterogeneous networks is transferred using the pseudo-label recursive propagation mechanism inspired by the concept of knowledge distillation. To the best of our knowledge, this is the first time to investigate the cross-sensor scene classification problem by constructing such a heterogeneous networks’ transfer scheme in RS fields. Our experiments using two cross-sensor RS datasets [aerial images $\rightarrow $ multispectral images (MSIs) and aerial images $\rightarrow $ hyper-spectral images (HSIs)] demonstrated that the proposed transfer learning strategy based on heterogeneous networks outperforms the supervised learning (SL) and fine-tune scheme for cross-sensor scene classification.


  • Fine-Grained Road Scene Understanding From Aerial Images Based on Semisupervised Semantic Segmentation Networks

    by Rong Xiao, Yuze Wang, Chao Tao

    High-precision electronic maps are required to provide more detailed and accurate information than traditional maps. With the rapid development of high-resolution remote sensing technology, it has become possible to extract fine-grained road scene information such as vehicles, road lines, zebra crossings, ground signs, and lane widths of roads from unmanned aerial vehicle (UAV) remote sensing images, which opens up opportunities for automatic mapping high-precision maps. The traditional method of deciphering remote sensing images is often obtained through manual visual interpretation. Due to the high cost and long lead time of this method, it leads to inefficiencies in updating large amounts of information. To address this problem, this letter models the fine-grained road scene understanding task as an image semantic segmentation problem and innovatively proposes a semisupervised fully convolutional neural network to extract the information efficiently at a low cost. Compared with the traditional supervised full convolutional neural network, this method can simultaneously optimize the standard supervised classification loss on labeled samples and the unsupervised consistency loss on unlabeled samples by using an integrated prediction technology and then input them to the end-to-end semantic segmentation network for training. This method is designed to effectively improve the classification accuracy of the semantic segmentation network and validly alleviates overfitting problems in the case of small numbers of labeled samples. In order to verify the effectiveness of this method, we constructed a data set for experimental, which is used to verify the effect of a variable number of unlabeled samples on model performance. Experimental results show that our method can efficiently complete the extraction of fine-grained road scene information such as vehicles, road lines, zebra crossings, ground signs, and lane widths of roads with a small number of labeled samples.