English
Related papers

Related papers: Large-Scale Data-Free Knowledge Distillation for I…

200 papers

Heterogeneity of data distributed across clients limits the performance of global models trained through federated learning, especially in the settings with highly imbalanced class distributions of local datasets. In recent years,…

Machine Learning · Computer Science 2023-04-11 Huancheng Chen , Johnny , Wang , Haris Vikalo

Quantization and Knowledge distillation (KD) methods are widely used to reduce memory and power consumption of deep neural networks (DNNs), especially for resource-constrained edge devices. Although their combination is quite promising to…

Computer Vision and Pattern Recognition · Computer Science 2019-12-02 Jangho Kim , Yash Bhalgat , Jinwon Lee , Chirag Patel , Nojun Kwak

Knowledge distillation (KD) has shown very promising capabilities in transferring learning representations from large models (teachers) to small models (students). However, as the capacity gap between students and teachers becomes larger,…

Computer Vision and Pattern Recognition · Computer Science 2023-03-24 Zengyu Qiu , Xinzhu Ma , Kunlin Yang , Chunya Liu , Jun Hou , Shuai Yi , Wanli Ouyang

Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more…

Computer Vision and Pattern Recognition · Computer Science 2021-06-18 Lin Wang , Kuk-Jin Yoon

Knowledge distillation (KD) is an effective tool for compressing deep classification models for edge devices. However, the performance of KD is affected by the large capacity gap between the teacher and student networks. Recent methods have…

Computer Vision and Pattern Recognition · Computer Science 2022-09-19 Ibtihel Amara , Maryam Ziaeefard , Brett H. Meyer , Warren Gross , James J. Clark

Due to privacy or patent concerns, a growing number of large models are released without granting access to their training data, making transferring their knowledge inefficient and problematic. In response, Data-Free Knowledge Distillation…

Machine Learning · Computer Science 2024-03-19 Zihao Tang , Zheqi Lv , Shengyu Zhang , Yifan Zhou , Xinyu Duan , Fei Wu , Kun Kuang

Knowledge distillation in machine learning is the process of transferring knowledge from a large model called the teacher to a smaller model called the student. Knowledge distillation is one of the techniques to compress the large network…

Machine Learning · Computer Science 2022-06-27 Durga Prasad Ganta , Himel Das Gupta , Victor S. Sheng

Data-free meta-learning (DFML) aims to enable efficient learning of new tasks by meta-learning from a collection of pre-trained models without access to the training data. Existing DFML work can only meta-learn from (i) white-box and (ii)…

Machine Learning · Computer Science 2025-02-18 Zixuan Hu , Li Shen , Zhenyi Wang , Baoyuan Wu , Chun Yuan , Dacheng Tao

Fully convolutional networks (FCNs) have become de facto tool to achieve very high-level performance for many vision and non-vision tasks in general and face recognition in particular. Such high-level accuracies are normally obtained by…

Computer Vision and Pattern Recognition · Computer Science 2019-06-04 Jayashree Karlekar , Jiashi Feng , Zi Sian Wong , Sugiri Pranata

Knowledge distillation (KD) is commonly deemed as an effective model compression technique in which a compact model (student) is trained under the supervision of a larger pretrained model or an ensemble of models (teacher). Various…

Machine Learning · Computer Science 2020-07-08 Fahad Sarfraz , Elahe Arani , Bahram Zonooz

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

Previous knowledge distillation (KD) methods mostly focus on compressing network architectures, which is not thorough enough in deployment as some costs like transmission bandwidth and imaging equipment are related to the image size.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-11 Guangyu Guo , Dingwen Zhang , Longfei Han , Nian Liu , Ming-Ming Cheng , Junwei Han

Federated learning (FL) supports distributed training of a global machine learning model across multiple devices with the help of a central server. However, data heterogeneity across different devices leads to the client model drift issue…

Machine Learning · Computer Science 2023-10-06 Xu Zhou , Xinyu Lei , Cong Yang , Yichun Shi , Xiao Zhang , Jingwen Shi

Knowledge distillation (KD) is a valuable technique for compressing large deep learning models into smaller, edge-suitable networks. However, conventional KD frameworks rely on pre-trained high-capacity teacher networks, which introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Hongjun Choi , Eun Som Jeon , Ankita Shukla , Pavan Turaga

Knowledge distillation has been applied to image classification successfully. However, object detection is much more sophisticated and most knowledge distillation methods have failed on it. In this paper, we point out that in object…

Computer Vision and Pattern Recognition · Computer Science 2022-03-10 Zhendong Yang , Zhe Li , Xiaohu Jiang , Yuan Gong , Zehuan Yuan , Danpei Zhao , Chun Yuan

The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Ali Abbasi , Ashkan Shahbazi , Hamed Pirsiavash , Soheil Kolouri

Knowledge distillation (KD) is generally considered as a technique for performing model compression and learned-label smoothing. However, in this paper, we study and investigate the KD approach from a new perspective: we study its efficacy…

Computer Vision and Pattern Recognition · Computer Science 2020-07-01 Nandan Kumar Jha , Rajat Saini , Sparsh Mittal

Knowledge distillation usually transfers the knowledge from a pre-trained cumbersome teacher network to a compact student network, which follows the classical teacher-teaching-student paradigm. Based on this paradigm, previous methods…

Computer Vision and Pattern Recognition · Computer Science 2021-10-14 Zheng Li , Xiang Li , Lingfeng Yang , Jian Yang , Zhigeng Pan

Knowledge distillation addresses the problem of transferring knowledge from a teacher model to a student model. In this process, we typically have multiple types of knowledge extracted from the teacher model. The problem is to make full use…

Computation and Language · Computer Science 2023-02-02 Chenglong Wang , Yi Lu , Yongyu Mu , Yimin Hu , Tong Xiao , Jingbo Zhu

In recent years, there has been a great deal of research in developing end-to-end speech recognition models, which enable simplifying the traditional pipeline and achieving promising results. Despite their remarkable performance…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-20 Ji Won Yoon , Hyeonseung Lee , Hyung Yong Kim , Won Ik Cho , Nam Soo Kim