Few-shot learning enables rapid generalization from extremely limited training examples. While previous efforts have utilized meta-learning or data augmentation methods to mitigate the problem of data scarcity, such approaches may struggle to maintain robustness and generalize effectively due to overfitting and noise sensitivity. In this article, we propose a novel approach, the semi-supervised label correction method for few-shot learning (SSLC-FSL), which leverages the data distribution of readily available and easily obtainable unlabeled data. SSLC-FSL iteratively corrects the labels of testing samples with alternating steps of pseudo-labeling and sample selection. The objective of pseudo-labeling is to repurpose graph-based semi-supervised learning for joint prediction of the entire testing set. We then introduce a modulation selection network (MSN) to rank testing samples by learning with noisy labels. The training set is expanded by selecting confident pseudo-labeled samples. In the MSN, a modulation aggregation layer is designed to encode support class information into each testing sample, thereby highlighting target category features and mitigating the negative impact of incorrect labels. The iterative label correction process is repeated until all testing samples are recalled to the expanded support set. To boost the SSLC-FSL algorithm, we pretrain a feature extractor to produce general-purpose representations. Particularly, we investigate two types of auxiliary tasks and their collaborative learning to acquire transferable visual information via an end-to-end multitask learning model. Our SSLC-FSL outperforms current state-of-the-art methods in any shot and all data settings, with up to +27.74% on standard remote sensing benchmarks and +5.70% on standard natural scene benchmarks.

GaoFen-5 (02) (GF5-02) is a new Chinese operational satellite that was launched on 7 September 2021. The Directional Polarimetric Camera (DPC) is one of the main payloads and is mainly used for the remote sensing monitoring of atmospheric components such as aerosols and water vapor. At present, the DPC is in the stage of on-orbit testing, and no public DPC precipitable water vapor (PWV) data are available. In this study, a PWV retrieval algorithm based on the spectral characteristics of DPC data is developed. The algorithm consists of three parts: (1) the construction of the lookup table, (2) the calculation of water vapor absorption transmittance (WVAT) in the band at 910 nm, and (3) DPC PWV retrieval. The global PWV results derived from DPC data are spatially continuous, which can illustrate the global distribution of water vapor content well. The validation based on the Aerosol Robotic Network (AERONET) PWV data shows that the DPC PWV data have accuracy similar to that of Moderate-resolution Imaging Spectroradiometer (MODIS) PWV data, with coefficient correlation of determination ($R^2$), mean absolute error (MAE), and relative error (RE) of 0.32, 0.30, and 0.93 using the DPC and 0.23, 0.36, and 0.96 using the MODIS, respectively. The results show that our proposed DPC PWV retrieval algorithm is feasible and has high accuracy. By analyzing the errors, we found that the calibration coefficients of the DPC in the 865 nm and 910 nm bands need to be updated.