English
Related papers

Related papers: DOT: A Distillation-Oriented Trainer

200 papers

Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of enhancing teacher…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Xin Zhang , Jianyang Xu , Hao Peng , Dongjing Wang , Jingyuan Zheng , Yu Li , Yuyu Yin , Hongbo Wang

Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…

Computation and Language · Computer Science 2021-09-24 Lei Li , Yankai Lin , Shuhuai Ren , Peng Li , Jie Zhou , Xu Sun

This paper addresses the problem of model compression via knowledge distillation. To this end, we propose a new knowledge distillation method based on transferring feature statistics, specifically the channel-wise mean and variance, from…

Computer Vision and Pattern Recognition · Computer Science 2020-03-11 Jing Yang , Brais Martinez , Adrian Bulat , Georgios Tzimiropoulos

Recent years have witnessed dramatically improvements in the knowledge distillation, which can generate a compact student model for better efficiency while retaining the model effectiveness of the teacher model. Previous studies find that:…

Computer Vision and Pattern Recognition · Computer Science 2021-11-04 Lehan Yang , Jincen Song

Knowledge distillation (KD) is an efficient approach to transfer the knowledge from a large "teacher" network to a smaller "student" network. Traditional KD methods require lots of labeled training samples and a white-box teacher…

Computer Vision and Pattern Recognition · Computer Science 2022-07-26 Dang Nguyen , Sunil Gupta , Kien Do , Svetha Venkatesh

Training models continually to detect and classify objects, from new classes and new domains, remains an open problem. In this work, we conduct a thorough analysis of why and how object detection models forget catastrophically. We focus on…

Computer Vision and Pattern Recognition · Computer Science 2022-10-10 Eli Verwimp , Kuo Yang , Sarah Parisot , Hong Lanqing , Steven McDonagh , Eduardo Pérez-Pellitero , Matthias De Lange , Tinne Tuytelaars

Leveraging knowledge from multiple tasks through introducing a small number of task specific parameters into each transformer layer, also known as adapters, receives much attention recently. However, adding an extra fusion layer to…

Machine Learning · Computer Science 2023-12-29 Junjie Wang , Yicheng Chen , Wangshu Zhang , Sen Hu , Teng Xu , Jing Zheng

Knowledge Distillation (KD) has proven effective for compressing large teacher models into smaller student models. While it is well known that student models can achieve similar accuracies as the teachers, it has also been shown that they…

Computer Vision and Pattern Recognition · Computer Science 2024-07-23 Amin Parchami-Araghi , Moritz Böhle , Sukrut Rao , Bernt Schiele

Algorithmic efficiency techniques such as distillation (\cite{hinton2015distillation}) are useful in improving model quality without increasing serving costs, provided a larger teacher model is available for a smaller student model to learn…

Machine Learning · Computer Science 2025-10-09 Khoa Trinh , Gaurav Menghani , Erik Vee

Knowledge distillation (KD) is a promising technique for model compression in neural machine translation. However, where the knowledge hides in KD is still not clear, which may hinder the development of KD. In this work, we first unravel…

Computation and Language · Computer Science 2024-07-18 Songming Zhang , Yunlong Liang , Shuaibo Wang , Wenjuan Han , Jian Liu , Jinan Xu , Yufeng Chen

Knowledge distillation (KD) is one of the prominent techniques for model compression. In this method, the knowledge of a large network (teacher) is distilled into a model (student) with usually significantly fewer parameters. KD tries to…

Machine Learning · Computer Science 2023-01-31 Aref Jafari , Mehdi Rezagholizadeh , Ali Ghodsi

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

Many recent breakthroughs in machine learning have been enabled by the pre-trained foundation models. By scaling up model parameters, training data, and computation resources, foundation models have significantly advanced the…

Artificial Intelligence · Computer Science 2023-10-06 Zhe Zhao , Qingyun Liu , Huan Gui , Bang An , Lichan Hong , Ed H. Chi

Knowledge distillation has been used to transfer knowledge learned by a sophisticated model (teacher) to a simpler model (student). This technique is widely used to compress model complexity. However, in most applications the compressed…

Machine Learning · Computer Science 2020-11-24 Hadi Pouransari , Mojan Javaheripi , Vinay Sharma , Oncel Tuzel

Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…

Computation and Language · Computer Science 2020-12-29 Peyman Passban , Yimeng Wu , Mehdi Rezagholizadeh , Qun Liu

While neural end-to-end text-to-speech (TTS) is superior to conventional statistical methods in many ways, the exposure bias problem in the autoregressive models remains an issue to be resolved. The exposure bias problem arises from the…

Computation and Language · Computer Science 2020-02-21 Rui Liu , Berrak Sisman , Jingdong Li , Feilong Bao , Guanglai Gao , Haizhou Li

In the context of resource-constrained environments such as embedded systems, adapting reduced-size foundation models to downstream tasks has become increasingly popular. This has recently motivated the emerging setting of task-specific…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Reda Bensaid , Yassir Bendou , Vincent Gripon , François Leduc-Primeau

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) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to generate Chain-of-Thoughts for reasoning tasks. KD methods typically ask the student to mimic the teacher's…

Computation and Language · Computer Science 2026-03-17 Minsang Kim , Seung Jun Baek

Knowledge distillation transfers knowledge from a high capacity teacher to a compact student using a mixture of hard and soft losses. On imbalanced data, a fixed weighting between hard and soft losses becomes brittle the learning process.…

Machine Learning · Computer Science 2026-05-20 Anh B. H. Nguyen , Ba Tho Phan , Viet Cuong Ta