High-dimensional imbalanced data presents the problems of massive invalid features and class imbalance, making it arduous for classifiers to gain respectable outcomes. Compared to the individual classifier, classifier ensemble has great potential to elevate the performance. In this paper, an adaptive progressive optimization ensemble approach (APOEA) is designed for high-dimensional imbalanced data classification. First, a local subview optimization (LSO) is designed, it enables each ensemble member to focus on learning information from different local regions, which helps to achieve dimensionality reduction while maintaining diversity. Then, an adaptive critical subview optimization (ACSO) is developed for supplemental learning, which can adaptively identify the suitable critical regions and execute critical subview optimization. Finally, based on the critical subview, APOEA implements an over-sampling scheme to mitigate the effect of class imbalance for base classifier. Experimental results demonstrate that our APOEA outperforms other mainstream imbalanced learning algorithms.
Yuyang Deng, Yu-Hong Xu, Pei-Jie Huang et al.· IEEE Transactions on Knowled...· 0 citations
3D visual grounding aims to localize the target object in a 3D scene from a natural language query, requiring both fine-grained semantic understanding and viewpoint-dependent spatial reasoning. Existing methods typically formulate semantic understanding as an auxiliary closed-set object classification task and rely on multi-view feature aggregation for viewpoint reasoning, limiting semantic generalization and weakening viewpoint-specific evidence. We observe that vision-language models naturally provide complementary capabilities through open-vocabulary semantic understanding and global scene perception. Based on this insight, we propose GuideGround, a VLM-guided framework that complements rather than replaces task-specific grounding models by leveraging VLMs for semantic enhancement and viewpoint-specific hypothesis verification. Specifically, we replace auxiliary closed-set object classification with VLM-generated object semantic descriptions to enhance semantic understanding. Meanwhile, instead of directly aggregating multi-view representations, we preserve viewpoint-specific grounding hypotheses through per-view grounding and explicitly verify them using VLMs across candidate viewpoints. Extensive experiments on the ReferIt3D benchmark demonstrate that GuideGround consistently outperforms previous state-of-the-art methods. Comprehensive ablation studies further confirm the effectiveness of both the proposed semantic understanding and viewpoint reasoning strategies.
Yiwen Wang, Yuyang Deng, Yihao Long et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
