3 papers
cs.CV2026
Disentangle-then-Align: Non-Iterative Hybrid Multimodal Image Registration via Cross-Scale Feature Disentanglement
Chunlei Zhang, Jiahao Xia, Yun Xiao +2
Multimodal image registration is a fundamental task and a prerequisite for downstream cross-modal analysis. Despite recent progress in shared feature extraction and multi-scale arc…
cs.CV2025
Unsupervised Part Discovery via Descriptor-Based Masked Image Restoration with Optimized Constraints
Jiahao Xia, Yike Wu, Wenjian Huang +2
Part-level features are crucial for image understanding, but few studies focus on them because of the lack of fine-grained labels. Although unsupervised part discovery can eliminat…
cs.LG2025
h-calibration: Rethinking Classifier Recalibration with Probabilistic Error-Bounded Objective
Wenjian Huang, Guiping Cao, Jiahao Xia +3
Deep neural networks have demonstrated remarkable performance across numerous learning tasks but often suffer from miscalibration, resulting in unreliable probability outputs. This…