English
Related papers

Related papers: Knowledge distillation: A good teacher is patient …

200 papers

Dataset distillation is the technique of synthesizing smaller condensed datasets from large original datasets while retaining necessary information to persist the effect. In this paper, we approach the dataset distillation problem from a…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Mingyang Chen , Bo Huang , Junda Lu , Bing Li , Yi Wang , Minhao Cheng , Wei Wang

Current scaling laws for visual AI models focus predominantly on large-scale pretraining, leaving a critical gap in understanding how performance scales for data-constrained downstream tasks. To address this limitation, this paper…

Machine Learning · Computer Science 2025-04-21 Wenxuan Yang , Qingqu Wei , Chenxi Ma , Weimin Tan , Bo Yan

Knowledge distillation refers to a technique of transferring the knowledge from a large learned model or an ensemble of learned models to a small model. This method relies on access to the original training set, which might not always be…

Machine Learning · Computer Science 2021-02-24 Xiaoyang Qu , Jianzong Wang , Jing Xiao

The emerging task of fine-grained image classification in low-data regimes assumes the presence of low inter-class variance and large intra-class variation along with a highly limited amount of training samples per class. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-07-01 Dmitry Demidov , Abduragim Shtanchaev , Mihail Mihaylov , Mohammad Almansoori

Knowledge distillation from pretrained visual representation models offers an effective approach to improve small, task-specific production models. However, the effectiveness of such knowledge transfer drops significantly when distilling…

Machine Learning · Computer Science 2025-07-01 Chengyu Dong , Huan Gui , Noveen Sachdeva , Long Jin , Ke Yin , Jingbo Shang , Lichan Hong , Ed H. Chi , Zhe Zhao

In the era of large scale pretrained models, Knowledge Distillation (KD) serves an important role in transferring the wisdom of computationally heavy teacher models to lightweight, efficient student models while preserving performance.…

Machine Learning · Computer Science 2023-11-07 Alex Wilf , Alex Tianyi Xu , Paul Pu Liang , Alexander Obolenskiy , Daniel Fried , Louis-Philippe Morency

Knowledge distillation deals with the problem of training a smaller model (Student) from a high capacity source model (Teacher) so as to retain most of its performance. Existing approaches use either the training data or meta-data extracted…

Machine Learning · Computer Science 2019-05-21 Gaurav Kumar Nayak , Konda Reddy Mopuri , Vaisakh Shaj , R. Venkatesh Babu , Anirban Chakraborty

Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training. Due to the cost of applying such models to…

Computation and Language · Computer Science 2019-09-27 Iulia Turc , Ming-Wei Chang , Kenton Lee , Kristina Toutanova

We survey various knowledge distillation (KD) strategies for simple classification tasks and implement a set of techniques that claim state-of-the-art accuracy. Our experiments using standardized model architectures, fixed compute budgets,…

Machine Learning · Computer Science 2019-12-24 Fabian Ruffy , Karanbir Chahal

Deep learning methods usually require a large amount of training data and lack interpretability. In this paper, we propose a novel knowledge distillation and model interpretation framework for medical image classification that jointly…

Computer Vision and Pattern Recognition · Computer Science 2022-01-13 Thanh Nguyen-Duc , He Zhao , Jianfei Cai , Dinh Phung

Fine-tuning large models is highly effective, however, inference can be expensive and produces carbon emissions. Knowledge distillation has been shown to be a practical solution to reduce inference costs, but the distillation process itself…

Computation and Language · Computer Science 2023-07-07 Junmo Kang , Wei Xu , Alan Ritter

Leveraging the capabilities of Knowledge Distillation (KD) strategies, we devise a strategy to fight the recent retraction of face recognition datasets. Given a pretrained Teacher model trained on a real dataset, we show that carefully…

Computer Vision and Pattern Recognition · Computer Science 2024-09-02 Pedro C. Neto , Ivona Colakovic , Sašo Karakatič , Ana F. Sequeira

Knowledge distillation has shown great success in classification, however, it is still challenging for detection. In a typical image for detection, representations from different locations may have different contributions to detection…

Computer Vision and Pattern Recognition · Computer Science 2022-01-07 Zijian Kang , Peizhen Zhang , Xiangyu Zhang , Jian Sun , Nanning Zheng

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

Model compression is critical for deploying deep learning models on resource-constrained devices. We introduce a novel method enhancing knowledge distillation with integrated gradients (IG) as a data augmentation strategy. Our approach…

Computer Vision and Pattern Recognition · Computer Science 2025-06-18 David E. Hernandez , Jose Chang , Torbjörn E. M. Nordling

Knowledge distillation (KD) has been a popular and effective method for model compression. One important assumption of KD is that the teacher's original dataset will also be available when training the student. However, in situations such…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Logan Frank , Jim Davis

Knowledge distillation (KD) is a widely adopted approach for compressing large neural networks by transferring knowledge from a large teacher model to a smaller student model. In the context of large language models, token level KD,…

Computation and Language · Computer Science 2025-09-19 Yihan Cao , Yanbin Kang , Zhengming Xing , Ruijie Jiang

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the…

Computation and Language · Computer Science 2026-01-16 Lechen Zhang , Yunxiang Zhang , Wei Hu , Lu Wang

Large language models (LLMs) have become increasingly prevalent in our daily lives, leading to an expectation for LLMs to be trustworthy -- - both accurate and well-calibrated (the prediction confidence should align with its ground truth…

Computation and Language · Computer Science 2024-10-04 KaShun Shum , Minrui Xu , Jianshu Zhang , Zixin Chen , Shizhe Diao , Hanze Dong , Jipeng Zhang , Muhammad Omer Raza

We propose a novel knowledge distillation approach to facilitate the transfer of dark knowledge from a teacher to a student. Contrary to most of the existing methods that rely on effective training of student models given pretrained…

Machine Learning · Computer Science 2022-01-25 Dae Young Park , Moon-Hyun Cha , Changwook Jeong , Dae Sin Kim , Bohyung Han