In the field of image recognition, the scale and diversity of datasets are crucial for model training. This study proposes a novel cross-validation dataset pruning method with data balancing (CVDP-DB). The method evaluates the correctness of training samples and their predicted probabilities, scoring them and subsequently performing precise pruning. We focus on pruning hard samples that are incorrectly predicted and easy samples that are correctly predicted with high probability, while retaining samples with high prediction uncertainty. These samples form a refined coreset for training models. This approach not only optimizes the feature distribution of the dataset but also enhances the model’s ability to recognize key samples. Experimental results show that the CVDP-DB method demonstrates excellent classification performance across various models and datasets. Notably, the applicability of CVDP-DB transcends the constraints of specific models or datasets, and the method surpasses state-of-the-art (SOTA) technologies.

Generative models have emerged as powerful tools capable of generating photorealistic images, spawning a wide range of applications across various domains. However, effectively integrating generative models into image classification tasks remains an open problem. Our analysis reveals that current generative data augmentation methods, as well as traditional data augmentation techniques, have limitations in simultaneously ensuring both fidelity (faithful foreground) and diversity (rich background contexts). To address this challenge, we propose Decomposition-Recomposition Data Augmentation (DRMix), an innovative intra-class data augmentation method. DRMix decomposes images into foreground-background and foreground parts, then performs diversified background recomposition and intra-class foreground recomposition, achieving dual diversity enhancement at both the image and part levels, and strikes a better trade-off between fidelity and diversity. Experimental results demonstrate that DRMix significantly improves performance across multiple tasks, including image classification, few-shot learning, and weakly-supervised object localization (WSOL).

Immigration transferring and new town construction in the Three Gorges Reservoir Areas have inevitably generated excavated slopes in this mountainous region. These excavated slopes, especially the high ones, have exerted impact on the environment and further potentially threatened the resident. Thus, the controlling of these excavated slopes and management of their spatial and attribute information has become vital in the construction of new towns for the immigrants. On the basis of MapObjects software platform, a synthesized geographical information system of excavated high slopes (EHSGIS) has been developed. In this practical system, field survey lists, filed check lists, documents, pictures and other information are managed by the data management subsystem. The inquiry of field survey information and field check information is separately managed by field survey information subsystem and check information subsystem. The inquiry of locations and regions, calculation of area and measurement of the distance of the slopes are accomplished in spatial distribution subsystem. The statistical analysis is specifically accomplished by statistical analysis subsystem. The 3D modeling subsystem realizes the quick browse of the real scene, such as the excavated slopes, construction, streets, etc. The system first proposes the framework of EHSGIS and realizes the integral management of spatial and attribute information of excavated slopes in Three Gorges Reservoir Areas. As a case study, 3D modeling of Yunyang town reappears the real scene. The system is helpful for invest appraisal and decision making in controlling of the excavated slopes in the Three Gorges Reservoir Areas.