paper-with-me

홈 › Papers

KD$^{2}$M: An unifying framework for feature knowledge distillation

2025-04-02 · Eduardo Fernandes Montesuma

Knowledge Distillation (KD) seeks to transfer the knowledge of a teacher, towards a student neural net. This process is often done by matching the networks' predictions (i.e., their output), but, recently several works have proposed to match the distributions of neural nets' activations (i.e., their features), a process known as \emph{distribution matching}. In this paper, we propose an unifying framework, Knowledge Distillation through Distribution Matching (KD$^{2}$M), which formalizes this strategy. Our contributions are threefold. We i) provide an overview of distribution metrics used in distribution matching, ii) benchmark on computer vision datasets, and iii) derive new theoretical results for KD.

📄 PDF Abstract BibTeX arXiv:2504.01757

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Asymmetric Decision-Making in Online Knowledge Distillation:Unifying Consensus and Divergence

2025-03-09 · Zhaowei Chen, Borui Zhao, Yuchen Ge, Yuhao Chen 외

Online Knowledge Distillation (OKD) methods streamline the distillation training process into a single stage, eliminating the need for knowledge transfer from a pretrained teacher network to a more compact student networ…

Decision MakingKnowledge DistillationSemantic SegmentationTransfer Learning

Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering

2023-07-20 · NeurIPS 2023 11

Despite the empirical success and practical significance of (relational) knowledge distillation that matches (the relations of) features between teacher and student models, the corresponding theoretical interpretations r…

ClusteringData AugmentationKnowledge Distillation

Unifying Heterogeneous Classifiers with Distillation

2019-04-12 · CVPR 2019 6 · Jayakorn Vongkulbhisal, Phongtharin Vinayavekhin, Marco Visentini-Scarzanella

In this paper, we study the problem of unifying knowledge from a set of classifiers with different architectures and target classes into a single classifier, given only a generic set of unlabelled data. We call this prob…

Knowledge Distillation

Teacher Supervision over Representation Equivalence Classes

2026-07-03 · Sang Il Han arxiv

Knowledge distillation is usually framed as a choice of what to match in the teacher - its logits, hidden features, or sample relations - which presupposes that the teacher's representation has absolute coordinates to ma…

Knowledge Distillation

Unifying distillation and privileged information

2015-11-11 · David Lopez-Paz, Léon Bottou, Bernhard Schölkopf, Vladimir Vapnik

Distillation (Hinton et al., 2015) and privileged information (Vapnik & Izmailov, 2015) are two techniques that enable machines to learn from other machines. This paper unifies these two techniques into generalized disti…