English
Related papers

Related papers: Intra-class Patch Swap for Self-Distillation

200 papers

Knowledge distillation (KD) has been actively studied for image classification tasks in deep learning, aiming to improve the performance of a student based on the knowledge from a teacher. However, applying KD in image regression with a…

Computer Vision and Pattern Recognition · Computer Science 2022-12-29 Xin Ding , Yongwei Wang , Zuheng Xu , Z. Jane Wang , William J. Welch

Knowledge Distillation (KD) has emerged as a promising technique for model compression but faces critical limitations: (1) sensitivity to hyperparameters requiring extensive manual tuning, (2) capacity gap when distilling from very large…

Machine Learning · Computer Science 2025-12-11 Gustavo Coelho Haase , Paulo Henrique Dourado da Silva

The generalization capability of deep neural networks has been substantially improved by applying a wide spectrum of regularization methods, e.g., restricting function space, injecting randomness during training, augmenting data, etc. In…

Machine Learning · Computer Science 2021-10-08 Kyungyul Kim , ByeongMoon Ji , Doyoung Yoon , Sangheum Hwang

Knowledge Distillation (KD) has been extensively used for natural language understanding (NLU) tasks to improve a small model's (a student) generalization by transferring the knowledge from a larger model (a teacher). Although KD methods…

Machine Learning · Computer Science 2022-12-13 Aref Jafari , Ivan Kobyzev , Mehdi Rezagholizadeh , Pascal Poupart , Ali Ghodsi

Knowledge distillation (KD) has been widely used for model compression and knowledge transfer. Typically, a big teacher model trained on sufficient data transfers knowledge to a small student model. However, despite the success of KD,…

Machine Learning · Computer Science 2022-12-20 Junzhuo Li , Xinwei Wu , Weilong Dong , Shuangzhi Wu , Chao Bian , Deyi Xiong

Knowledge distillation (KD) has become a widely adopted approach for compressing large language models (LLMs) to reduce computational costs and memory footprints. However, the availability of complex teacher models is a prerequisite for…

Computation and Language · Computer Science 2024-11-27 Yao Fu , Yin Yu , Xiaotian Han , Runchao Li , Xianxuan Long , Haotian Yu , Pan Li

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

Deep neural networks (DNNs) have improved NLP tasks significantly, but training and maintaining such networks could be costly. Model compression techniques, such as, knowledge distillation (KD), have been proposed to address the issue;…

Computation and Language · Computer Science 2023-11-08 Manas Mohanty , Tanya Roosta , Peyman Passban

Does Knowledge Distillation (KD) really work? Conventional wisdom viewed it as a knowledge transfer procedure where a perfect mimicry of the student to its teacher is desired. However, paradoxical studies indicate that closely replicating…

Machine Learning · Computer Science 2024-05-03 Chenqi Guo , Shiwei Zhong , Xiaofeng Liu , Qianli Feng , Yinglong Ma

Incremental learning methods can learn new classes continually by distilling knowledge from the last model (as a teacher model) to the current model (as a student model) in the sequentially learning process. However, these methods cannot…

Computer Vision and Pattern Recognition · Computer Science 2022-02-25 Longhui Yu , Zhenyu Weng , Yuqing Wang , Yuesheng Zhu

Knowledge distillation(KD) aims to improve the performance of a student network by mimicing the knowledge from a powerful teacher network. Existing methods focus on studying what knowledge should be transferred and treat all samples equally…

Computer Vision and Pattern Recognition · Computer Science 2020-08-05 Youcai Zhang , Zhonghao Lan , Yuchen Dai , Fangao Zeng , Yan Bai , Jie Chang , Yichen Wei

Knowledge distillation (KD) enables a smaller "student" model to mimic a larger "teacher" model by transferring knowledge from the teacher's output or features. However, most KD methods treat all samples uniformly, overlooking the varying…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Chi-Ping Su , Ching-Hsun Tseng , Bin Pu , Lei Zhao , Jiewen Yang , Zhuangzhuang Chen , Shin-Jye Lee

Knowledge distillation (KD) has been extensively employed to transfer the knowledge from a large teacher model to the smaller students, where the parameters of the teacher are fixed (or partially) during training. Recent studies show that…

Machine Learning · Computer Science 2022-06-01 Jun Rao , Xv Meng , Liang Ding , Shuhan Qi , Dacheng Tao

Knowledge distillation (KD) is a key technique for compressing large language models into smaller ones while preserving performance. Despite the recent traction of KD research, its effectiveness for smaller language models (LMs) and the…

Computation and Language · Computer Science 2025-08-05 Suhas Kamasetty Ramesh , Ayan Sengupta , Tanmoy Chakraborty

Neural network potentials (NNPs) offer a powerful alternative to traditional force fields for molecular dynamics (MD) simulations. Accurate and stable MD simulations, crucial for evaluating material properties, require training data…

Machine Learning · Computer Science 2025-06-23 Naoki Matsumura , Yuta Yoshimoto , Yuto Iwasaki , Meguru Yamazaki , Yasufumi Sakai

Knowledge Distillation (KD) transfers knowledge from a large pre-trained teacher network to a compact and efficient student network, making it suitable for deployment on resource-limited media terminals. However, traditional KD methods…

Computer Vision and Pattern Recognition · Computer Science 2024-09-23 Xinlei Huang , Jialiang Tang , Xubin Zheng , Jinjia Zhou , Wenxin Yu , Ning Jiang

Knowledge distillation (KD) requires sufficient data to transfer knowledge from large-scale teacher models to small-scale student models. Therefore, data augmentation has been widely used to mitigate the shortage of data under specific…

Computation and Language · Computer Science 2023-05-23 Ziqi Wang , Chi Han , Wenxuan Bao , Heng Ji

Knowledge distillation (KD) has been widely used to improve the test accuracy of a "student" network, by training it to mimic the soft probabilities of a trained "teacher" network. Yet, it has been shown in recent work that, despite being…

Machine Learning · Computer Science 2024-03-20 Vaishnavh Nagarajan , Aditya Krishna Menon , Srinadh Bhojanapalli , Hossein Mobahi , Sanjiv Kumar

Intermediate layer knowledge distillation (KD) can improve the standard KD technique (which only targets the output of teacher and student models) especially over large pre-trained language models. However, intermediate layer distillation…

Computation and Language · Computer Science 2021-10-05 Md Akmal Haidar , Nithin Anchuri , Mehdi Rezagholizadeh , Abbas Ghaddar , Philippe Langlais , Pascal Poupart

Knowledge distillation is a powerful method for model compression, enabling the efficient deployment of complex deep learning models (teachers), including large language models. However, its underlying statistical mechanisms remain unclear,…

Methodology · Statistics 2026-05-28 Luyang Fang , Yongkai Chen , Jiazhang Cai , Ping Ma , Wenxuan Zhong