English
Related papers

Related papers: Bezier Distillation

200 papers

Model compression has been widely adopted to obtain light-weighted deep neural networks. Most prevalent methods, however, require fine-tuning with sufficient training data to ensure accuracy, which could be challenged by privacy and…

Machine Learning · Computer Science 2020-05-05 Haoli Bai , Jiaxiang Wu , Irwin King , Michael Lyu

Knowledge distillation aims to learn a lightweight student network from a pre-trained teacher network. In practice, existing knowledge distillation methods are usually infeasible when the original training data is unavailable due to some…

Computer Vision and Pattern Recognition · Computer Science 2023-07-24 Jialiang Tang , Shuo Chen , Gang Niu , Masashi Sugiyama , Chen Gong

Convolutional neural networks have been widely deployed in various application scenarios. In order to extend the applications' boundaries to some accuracy-crucial domains, researchers have been investigating approaches to boost accuracy…

Machine Learning · Computer Science 2019-05-21 Linfeng Zhang , Jiebo Song , Anni Gao , Jingwei Chen , Chenglong Bao , Kaisheng Ma

Unlike existing knowledge distillation methods focus on the baseline settings, where the teacher models and training strategies are not that strong and competing as state-of-the-art approaches, this paper presents a method dubbed DIST to…

Computer Vision and Pattern Recognition · Computer Science 2022-12-29 Tao Huang , Shan You , Fei Wang , Chen Qian , Chang Xu

Distillation has shown remarkable success in transferring knowledge from a Large Language Model (LLM) teacher to a student LLM. However, current distillation methods require similar tokenizers between the teacher and the student,…

Computation and Language · Computer Science 2025-10-27 Benjamin Minixhofer , Ivan Vulić , Edoardo Maria Ponti

Compressing deep networks is essential to expand their range of applications to constrained settings. The need for compression however often arises long after the model was trained, when the original data might no longer be available. On…

Machine Learning · Computer Science 2022-01-19 Jean-Michel Begon , Pierre Geurts

Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model…

Knowledge distillation is an effective approach to learn compact models (students) with the supervision of large and strong models (teachers). As empirically there exists a strong correlation between the performance of teacher and student…

Machine Learning · Computer Science 2022-10-13 Chaofei Wang , Qisen Yang , Rui Huang , Shiji Song , Gao Huang

Knowledge Distillation (KD) aims to learn a compact student network using knowledge from a large pre-trained teacher network, where both networks are trained on data from the same distribution. However, in practical applications, the…

Machine Learning · Computer Science 2024-01-17 Jialiang Tang , Shuo Chen , Gang Niu , Hongyuan Zhu , Joey Tianyi Zhou , Chen Gong , Masashi Sugiyama

Knowledge distillation is one of the most effective methods for model compression. Previous studies have focused on the student model effectively training the predictive distribution of the teacher model. However, during training, the…

Computation and Language · Computer Science 2026-01-29 Junseok Lee , Nahoon Kim , Sangyong Lee , Chang-Jae Chun

Knowledge distillation is a critical technique to transfer knowledge between models, typically from a large model (the teacher) to a more fine-grained one (the student). The objective function of knowledge distillation is typically the…

Computation and Language · Computer Science 2021-06-03 Xinyu Wang , Yong Jiang , Zhaohui Yan , Zixia Jia , Nguyen Bach , Tao Wang , Zhongqiang Huang , Fei Huang , Kewei Tu

Deep models are susceptible to learning spurious correlations, even during the post-processing. We take a closer look at the knowledge distillation -- a popular post-processing technique for model compression -- and find that distilling…

Machine Learning · Computer Science 2023-02-23 Jiwoon Lee , Jaeho Lee

Multilingual machine translation, which translates multiple languages with a single model, has attracted much attention due to its efficiency of offline training and online serving. However, traditional multilingual translation usually…

Computation and Language · Computer Science 2019-05-01 Xu Tan , Yi Ren , Di He , Tao Qin , Zhou Zhao , Tie-Yan Liu

Diffusion- and flow-based models have emerged as state-of-the-art generative modeling approaches, but they require many sampling steps. Consistency models can distill these models into efficient one-step generators; however, unlike flow-…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 Amirmojtaba Sabour , Sanja Fidler , Karsten Kreis

The expansion of neural network sizes and the enhanced resolution of modern image sensors result in heightened memory and power demands to process modern computer vision models. In order to deploy these models in extremely…

Computer Vision and Pattern Recognition · Computer Science 2025-04-29 Fang Chen , Gourav Datta , Mujahid Al Rafi , Hyeran Jeon , Meng Tang

Knowledge distillation involves transferring the predictive capabilities of large, high-performing AI models (teachers) to smaller models (students) that can operate in environments with limited computing power. In this paper, we address…

Machine Learning · Computer Science 2026-01-12 Pattarawat Chormai , Ali Hashemi , Klaus-Robert Müller , Grégoire Montavon

Knowledge distillation is widely used to improve generalization in practice, yet its theoretical understanding remains elusive. In the standard distillation setting, a teacher model provides soft predictions to guide the training of a…

Information Theory · Computer Science 2026-05-18 Bingying Li , Haiyun He

Distillation is the technique of training a "student" model based on examples that are labeled by a separate "teacher" model, which itself is trained on a labeled dataset. The most common explanations for why distillation "works" are…

To circumvent the non-parallelizability of recurrent neural network-based equalizers, we propose knowledge distillation to recast the RNN into a parallelizable feedforward structure. The latter shows 38\% latency decrease, while impacting…

Normalizing flows are a powerful class of generative models demonstrating strong performance in several speech and vision problems. In contrast to other generative models, normalizing flows are latent variable models with tractable…

Machine Learning · Computer Science 2021-08-06 Dmitry Baranchuk , Vladimir Aliev , Artem Babenko