English
Related papers

Related papers: A Layered Self-Supervised Knowledge Distillation F…

200 papers

Knowledge distillation is a popular technique for transferring the knowledge from a large teacher model to a smaller student model by mimicking. However, distillation by directly aligning the feature maps between teacher and student may…

Computer Vision and Pattern Recognition · Computer Science 2023-03-27 Ziwei Liu , Yongtao Wang , Xiaojie Chu

Knowledge distillation (KD) is a common approach to compress a teacher model to reduce its inference cost and memory footprint, by training a smaller student model. However, in the context of autoregressive language models (LMs), we…

Computation and Language · Computer Science 2024-06-18 Qihuang Zhong , Liang Ding , Li Shen , Juhua Liu , Bo Du , Dacheng Tao

Deep neural networks have achieved remarkable performance for artificial intelligence tasks. The success behind intelligent systems often relies on large-scale models with high computational complexity and storage costs. The…

Computer Vision and Pattern Recognition · Computer Science 2023-06-21 Chuanguang Yang , Xinqiang Yu , Zhulin An , Yongjun Xu

Consistency regularization has been widely studied in recent semisupervised semantic segmentation methods, and promising performance has been achieved. In this work, we propose a new consistency regularization framework, termed mutual…

Computer Vision and Pattern Recognition · Computer Science 2023-08-31 Jianlong Yuan , Jinchao Ge , Zhibin Wang , Yifan Liu

Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands. Knowledge Distillation (KD) has emerged as an effective strategy to improve…

This paper studies the potential of distilling knowledge from pre-trained models, especially Masked Autoencoders. Our approach is simple: in addition to optimizing the pixel reconstruction loss on masked inputs, we minimize the distance…

Computer Vision and Pattern Recognition · Computer Science 2022-11-11 Yutong Bai , Zeyu Wang , Junfei Xiao , Chen Wei , Huiyu Wang , Alan Yuille , Yuyin Zhou , Cihang Xie

In real applications, different computation-resource devices need different-depth networks (e.g., ResNet-18/34/50) with high-accuracy. Usually, existing methods either design multiple networks and train them independently, or construct…

Computer Vision and Pattern Recognition · Computer Science 2021-08-11 Qi Zhao , Shuchang Lyu , Zhiwei Zhang , Ting-Bing Xu , Guangliang Cheng

Knowledge distillation (KD) is a standard route to compress Large Language Models (LLMs) into compact students, yet most pipelines uniformly apply token-wise loss regardless of teacher confidence. This indiscriminate supervision amplifies…

Computation and Language · Computer Science 2025-11-18 Haiduo Huang , Jiangcheng Song , Yadong Zhang , Pengju Ren

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

Computer Vision and Pattern Recognition · Computer Science 2020-06-24 Ruoyu Sun , Fuhui Tang , Xiaopeng Zhang , Hongkai Xiong , Qi Tian

Knowledge Distillation (KD) compresses large language models (LLMs) by transferring the teacher model's capabilities to a smaller student model, reducing inference cost and memory usage while maintaining performance. However, existing KD…

Computation and Language · Computer Science 2025-06-11 Lingyuan Liu , Mengxiang Zhang

Sparse neural systems are gaining traction for efficient continual learning due to their modularity and low interference. Architectures such as Sparse Distributed Memory Multi-Layer Perceptrons (SDMLP) construct task-specific subnetworks…

Machine Learning · Computer Science 2025-12-18 Huiyan Xue , Xuming Ran , Yaxin Li , Qi Xu , Enhui Li , Yi Xu , Qiang Zhang

Knowledge distillation (KD) is a widely used technique to transfer knowledge from a large teacher network to a smaller student model. Traditional KD uses a fixed balancing factor alpha as a hyperparameter to combine the hard-label…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Zhengda Li

Knowledge distillation (KD) aims at improving the performance of a compact student model by distilling the knowledge from a high-performing teacher model. In this paper, we present an adaptive KD approach, namely AdaDistill, for deep face…

Computer Vision and Pattern Recognition · Computer Science 2024-07-02 Fadi Boutros , Vitomir Štruc , Naser Damer

Knowledge distillation (KD) is an effective framework to transfer knowledge from a large-scale teacher to a compact yet well-performing student. Previous KD practices for pre-trained language models mainly transfer knowledge by aligning…

Computation and Language · Computer Science 2022-11-03 Lean Wang , Lei Li , Xu Sun

The holy grail in deep neural network research is porting the memory- and computation-intensive network models on embedded platforms with a minimal compromise in model accuracy. To this end, we propose a novel approach, termed as…

Machine Learning · Computer Science 2019-10-29 Srinidhi Hegde , Ranjitha Prasad , Ramya Hebbalaguppe , Vishwajith Kumar

High storage and computational costs obstruct deep neural networks to be deployed on resource-constrained devices. Knowledge distillation aims to train a compact student network by transferring knowledge from a larger pre-trained teacher…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Haoran Zhao , Xin Sun , Junyu Dong , Changrui Chen , Zihe Dong

Data-free knowledge distillation~(DFKD) is an effective manner to solve model compression and transmission restrictions while retaining privacy protection, which has attracted extensive attention in recent years. Currently, the majority of…

Machine Learning · Computer Science 2025-10-07 Renrong Shao , Wei Zhang , Jun wang

As a promising solution for model compression, knowledge distillation (KD) has been applied in recommender systems (RS) to reduce inference latency. Traditional solutions first train a full teacher model from the training data, and then…

Information Retrieval · Computer Science 2022-11-29 Gang Chen , Jiawei Chen , Fuli Feng , Sheng Zhou , Xiangnan He

This study presents a novel approach for knowledge distillation (KD) from a BERT teacher model to an automatic speech recognition (ASR) model using intermediate layers. To distil the teacher's knowledge, we use an attention decoder that…

Computation and Language · Computer Science 2024-01-23 Michael Hentschel , Yuta Nishikawa , Tatsuya Komatsu , Yusuke Fujita

Semi-supervised regression (SSR), which aims to predict continuous scores for samples while reducing the reliance on large-scale labeled data, has recently attracted considerable attention across various applications, including computer…

Machine Learning · Computer Science 2026-05-28 Ye Su , Hezhe Qiao , Wei Huang , Lin Chen