8 papers
MobileGeo: Exploring Hierarchical Knowledge Distillation for Resource-Efficient Cross-view Drone Geo-Localization
Jian Sun, Kangdao Liu, Chi Zhang +4
Cross-view geo-localization (CVGL) plays a vital role in drone-based multimedia applications, enabling precise localization by matching drone-captured aerial images against geo-tag…
Exploring the Noise Robustness of Online Conformal Prediction
Huajun Xi, Kangdao Liu, Hao Zeng +2
Conformal prediction is an emerging technique for uncertainty quantification that constructs prediction sets guaranteed to contain the true label with a predefined probability. Rec…
Online Conformal Selection with Accept-to-Reject Changes
Kangdao Liu, Huajun Xi, Chi-Man Vong +1
Selecting a subset of promising candidates from a large pool is crucial across various scientific and real-world applications. Conformal selection offers a distribution-free and mo…
Parametric Scaling Law of Tuning Bias in Conformal Prediction
Hao Zeng, Kangdao Liu, Bingyi Jing +1
Conformal prediction is a popular framework of uncertainty quantification that constructs prediction sets with coverage guarantees. To uphold the exchangeability assumption, many c…
3D Hand Mesh-Guided AI-Generated Malformed Hand Refinement with Hand Pose Transformation via Diffusion Model
Chen-Bin Feng, Kangdao Liu, Jian Sun +3
The malformed hands in the AI-generated images seriously affect the authenticity of the images. To refine malformed hands, existing depth-based approaches use a hand depth estimato…
C-Adapter: Adapting Deep Classifiers for Efficient Conformal Prediction Sets
Kangdao Liu, Hao Zeng, Jianguo Huang +3
Conformal prediction, as an emerging uncertainty quantification technique, typically functions as post-hoc processing for the outputs of trained classifiers. To optimize the classi…