5 papers
Variational Adapter for Cross-modal Similarity Representation
WenZhang Wei, Zhipeng Gui, Dehua Peng +2
The core of vision-language models lies in measuring cross-modal similarity within a unified representation space. However, most image-text matching or multi-class image classifica…
Sampling-enabled scalable manifold learning unveils the discriminative cluster structure of high-dimensional data
Dehua Peng, Zhipeng Gui, Wenzhang Wei +4
As a pivotal branch of machine learning, manifold learning uncovers the intrinsic low-dimensional structure within complex nonlinear manifolds in high-dimensional space for visuali…
AutoGEEval++: A Multi-Level and Multi-Geospatial-Modality Automated Evaluation Framework for Large Language Models in Geospatial Code Generation on Google Earth Engine
Shuyang Hou, Zhangxiao Shen, Huayi Wu +10
Geospatial code generation is becoming a key frontier in integrating artificial intelligence with geo-scientific analysis, yet standardised automated evaluation tools for this task…
Interpreting the Curse of Dimensionality from Distance Concentration and Manifold Effect
Dehua Peng, Zhipeng Gui, Huayi Wu
The characteristics of data like distribution and heterogeneity, become more complex and counterintuitive as dimensionality increases. This phenomenon is known as curse of dimensio…
A Robust and Efficient Boundary Point Detection Method by Measuring Local Direction Dispersion
Dehua Peng, Zhipeng Gui, Jie Gui +1
Boundary point detection aims to outline the external contour structure of clusters and enhance the inter-cluster discrimination, thus bolstering the performance of the downstream…