No abstract

Image classification is a key task in image understanding, and multi-label image classification has become a popular topic in recent years. However, the success of multi-label image classification is closely related to the way of constructing a training set. As active learning aims to construct an effective training set through iteratively selecting the most informative examples to query labels from annotators, it was introduced into multi-label image classification. Accordingly, multi-label active learning is becoming an important research direction. In this work, we first review existing multi-label active learning algorithms for image classification. These algorithms can be categorized into two top groups from two aspects respectively: sampling and annotation. The most important component of multi-label active learning is to design an effective sampling strategy that actively selects the examples with the highest informativeness from an unlabeled data pool, according to various information measures. Thus, different informativeness measures are emphasized in this survey. Furthermore, this work also makes a deep investigation on existing challenging issues and future promises in multi-label active learning with a focus on four core aspects: example dimension, label dimension, annotation, and application extension.

No abstract

Accurate and timely information on crop planting patterns is crucial for research on sustainable agriculture, regional resources, and food security. However, existing spatial datasets have few high-precision and wide-range planting pattern maps. The production may be limited by the unbalanced spatiotemporal resolution, insufficient massive field sample data, low local computer processing speed, and other factors. To overcome these limitations, we proposed semi-automatic expansion and spatiotemporal migration strategies for sample points and performed a pixel-and-phenology-based random forest algorithm on the Google Earth Engine platform to generate crop planting pattern maps at high spatiotemporal resolution by integrating Landsat-8 and Sentinel-2 time series image data. In this study, we report planting pattern maps for 2017–2021 at a 10-m spatial resolution of the Jianghan Plain, including six crops and nine planting patterns, with an overall accuracy of 84–94% and a kappa coefficient of 0.80–0.93. The spatiotemporal distribution is driven by multiple factors, such as subjectivity and social economy. This research indicates that the proposed approach is effective for mapping large-scale planting patterns and can be readily applied to other regions.

No abstract