English
Related papers

Related papers: Sparse Knowledge Distillation: A Mathematical Fram…

200 papers

In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection…

Computer Vision and Pattern Recognition · Computer Science 2024-02-02 Roy Miles , Krystian Mikolajczyk

This paper presents a novel knowledge distillation based model compression framework consisting of a student ensemble. It enables distillation of simultaneously learnt ensemble knowledge onto each of the compressed student models. Each…

Computer Vision and Pattern Recognition · Computer Science 2020-11-17 Devesh Walawalkar , Zhiqiang Shen , Marios Savvides

Knowledge distillation (KD) has proved to be an effective approach for deep neural network compression, which learns a compact network (student) by transferring the knowledge from a pre-trained, over-parameterized network (teacher). In…

Machine Learning · Computer Science 2021-04-13 Zi Wang

Knowledge distillation aims to compress a powerful yet cumbersome teacher model into a lightweight student model without much sacrifice of performance. For this purpose, various approaches have been proposed over the past few years,…

Computer Vision and Pattern Recognition · Computer Science 2022-03-29 Defang Chen , Jian-Ping Mei , Hailin Zhang , Can Wang , Yan Feng , Chun Chen

On-policy self-distillation, where a student is pulled toward a copy of itself conditioned on privileged context (e.g., a verified solution or feedback), offers a promising direction for advancing reasoning capability without a stronger…

Machine Learning · Computer Science 2026-05-13 Guobin Shen , Xiang Cheng , Chenxiao Zhao , Lei Huang , Jindong Li , Dongcheng Zhao , Xing Yu

The performance of a distillation-based compressed network is governed by the quality of distillation. The reason for the suboptimal distillation of a large network (teacher) to a smaller network (student) is largely attributed to the gap…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Vibhas Vats , David Crandall

Despite the recent works on knowledge distillation (KD) have achieved a further improvement through elaborately modeling the decision boundary as the posterior knowledge, their performance is still dependent on the hypothesis that the…

Computer Vision and Pattern Recognition · Computer Science 2019-11-14 Junjie Liu , Dongchao Wen , Hongxing Gao , Wei Tao , Tse-Wei Chen , Kinya Osa , Masami Kato

Knowledge distillation from Large Language Models (LLMs) to smaller models has emerged as a critical technique for deploying efficient AI systems. However, current methods for distillation via synthetic data lack pedagogical awareness,…

Artificial Intelligence · Computer Science 2026-02-13 Bowei He , Yankai Chen , Xiaokun Zhang , Linghe Kong , Philip S. Yu , Xue Liu , Chen Ma

Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always…

Machine Learning · Computer Science 2019-12-06 Defang Chen , Jian-Ping Mei , Can Wang , Yan Feng , Chun Chen

Both accuracy and efficiency are of significant importance to the task of semantic segmentation. Existing deep FCNs suffer from heavy computations due to a series of high-resolution feature maps for preserving the detailed knowledge in…

Computer Vision and Pattern Recognition · Computer Science 2019-03-13 Tong He , Chunhua Shen , Zhi Tian , Dong Gong , Changming Sun , Youliang Yan

In the context of label-efficient learning on video data, the distillation method and the structural design of the teacher-student architecture have a significant impact on knowledge distillation. However, the relationship between these…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Chao Wang , Zheng Tang

Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as…

Computation and Language · Computer Science 2020-01-17 Gustavo Aguilar , Yuan Ling , Yu Zhang , Benjamin Yao , Xing Fan , Chenlei Guo

In this work, we propose a novel information theoretic framework for dictionary learning (DL) and sparse coding (SC) on a statistical manifold (the manifold of probability distributions). Unlike the traditional DL and SC framework, our new…

Computer Vision and Pattern Recognition · Computer Science 2017-02-06 Rudrasis Chakraborty , Monami Banerjee , Victoria Crawford , Baba C. Vemuri

Knowledge Distillation (KD) is a common knowledge transfer algorithm used for model compression across a variety of deep learning based natural language processing (NLP) solutions. In its regular manifestations, KD requires access to the…

Computation and Language · Computer Science 2021-01-01 Ahmad Rashid , Vasileios Lioutas , Abbas Ghaddar , Mehdi Rezagholizadeh

Knowledge distillation is an effective way for model compression in deep learning. Given a large model (i.e., teacher model), it aims to improve the performance of a compact model (i.e., student model) by transferring the information from…

Machine Learning · Computer Science 2022-03-31 Qi Qian , Hao Li , Juhua Hu

Knowledge distillation is a technique used to train a small student network using the output generated by a large teacher network, and has many empirical advantages~\citep{Hinton2015DistillingTK}. While the standard one-shot approach to…

Machine Learning · Computer Science 2025-03-25 Shivam Gupta , Sushrut Karmalkar

Knowledge Distillation refers to a class of methods that transfers the knowledge from a teacher network to a student network. In this paper, we propose Sparse Representation Matching (SRM), a method to transfer intermediate knowledge…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Dat Thanh Tran , Moncef Gabbouj , Alexandros Iosifidis

It is well known that a speech recognition system that combines multiple acoustic models trained on the same data significantly outperforms a single-model system. Unfortunately, real time speech recognition using a whole ensemble of models…

Computation and Language · Computer Science 2019-06-27 Zhenchuan Yang , Chun Zhang , Weibin Zhang , Jianxiu Jin , Dongpeng Chen

This work introduces and rigorously analyzes a novel operator-splitting finite element scheme for approximating viscosity solutions of a broad class of constrained second-order partial differential equations. By decoupling the primary PDE…

Numerical Analysis · Mathematics 2025-07-01 Po-Yi Wu

Top-performing machine learning systems, such as deep neural networks, large ensembles and complex probabilistic graphical models, can be expensive to store, slow to evaluate and hard to integrate into larger systems. Ideally, we would like…

Machine Learning · Statistics 2015-10-09 George Papamakarios