Guangda Ji — accepted AI-conference papers

2025

ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding

Guangda Ji, Silvan Weder, Francis Engelmann, Marc Pollefeys, Hermann Blum

CVPR 2025poster

Neural network performance scales with both model size and data volume, as shown in both language and image processing. This requires scaling-friendly architectures and large datasets. While transformers have been adapted for 3D vision, a `GPT-moment' remains elusive due to limited training data. We…

Cited by 4 Source ↗PDF ↗code ↗Scholar ↗

2020

Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher

Guangda Ji, Zhanxing Zhu

NeurIPS 2020poster

Knowledge distillation is a strategy of training a student network with guide of the soft output from a teacher network. It has been a successful method of model compression and knowledge transfer. However, currently knowledge distillation lacks a convincing theoretical understanding. On the other h…

Cited by 52 Source ↗PDF ↗Scholar ↗