English

Precise Knowledge Transfer via Flow Matching

Computer Vision and Pattern Recognition 2024-02-06 v1

Abstract

In this paper, we propose a novel knowledge transfer framework that introduces continuous normalizing flows for progressive knowledge transformation and leverages multi-step sampling strategies to achieve precision knowledge transfer. We name this framework Knowledge Transfer with Flow Matching (FM-KT), which can be integrated with a metric-based distillation method with any form (\textit{e.g.} vanilla KD, DKD, PKD and DIST) and a meta-encoder with any available architecture (\textit{e.g.} CNN, MLP and Transformer). By introducing stochastic interpolants, FM-KD is readily amenable to arbitrary noise schedules (\textit{e.g.}, VP-ODE, VE-ODE, Rectified flow) for normalized flow path estimation. We theoretically demonstrate that the training objective of FM-KT is equivalent to minimizing the upper bound of the teacher feature map or logit negative log-likelihood. Besides, FM-KT can be viewed as a unique implicit ensemble method that leads to performance gains. By slightly modifying the FM-KT framework, FM-KT can also be transformed into an online distillation framework OFM-KT with desirable performance gains. Through extensive experiments on CIFAR-100, ImageNet-1k, and MS-COCO datasets, we empirically validate the scalability and state-of-the-art performance of our proposed methods among relevant comparison approaches.

Keywords

Cite

@article{arxiv.2402.02012,
  title  = {Precise Knowledge Transfer via Flow Matching},
  author = {Shitong Shao and Zhiqiang Shen and Linrui Gong and Huanran Chen and Xu Dai},
  journal= {arXiv preprint arXiv:2402.02012},
  year   = {2024}
}
R2 v1 2026-06-28T14:36:56.921Z