Frank de Hoog — accepted AI-conference papers

2025

Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets

Yudong Chen, Xuwei Xu, Frank de Hoog, Jiajun Liu, Sen Wang

ICLR 2025poster

This paper tackles a new problem of dataset pruning for Knowledge Distillation (KD), from a fresh perspective of Decision Boundary (DB) preservation and drifts. Existing dataset pruning methods generally assume that the post-pruning DB formed by the selected samples can be well-captured by future ne…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2022

Improved Feature Distillation via Projector Ensemble

Yudong Chen, Sen Wang, Jiajun Liu, Xuwei Xu, Frank de Hoog, Zi Huang

NeurIPS 2022accept

In knowledge distillation, previous feature distillation methods mainly focus on the design of loss functions and the selection of the distilled layers, while the effect of the feature projector between the student and the teacher remains under-explored. In this paper, we first discuss a plausible m…

Cited by 50 Source ↗PDF ↗code ↗Scholar ↗