English
Related papers

Related papers: Regularizing Class-wise Predictions via Self-knowl…

200 papers

The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods…

Computer Vision and Pattern Recognition · Computer Science 2025-11-21 George Cazenavette , Antonio Torralba , Vincent Sitzmann

Knowledge distillation, a technique recently gaining popularity for enhancing model generalization in Convolutional Neural Networks (CNNs), operates under the assumption that both teacher and student models are trained on identical data…

Machine Learning · Computer Science 2024-12-06 Can Wang , Zhe Wang , Defang Chen , Sheng Zhou , Yan Feng , Chun Chen

Knowledge distillation allows transferring knowledge from a pre-trained model to another. However, it suffers from limitations, and constraints related to the two models need to be architecturally similar. Knowledge distillation addresses…

Image and Video Processing · Electrical Eng. & Systems 2020-09-03 Sajjad Abbasi , Mohsen Hajabdollahi , Pejman Khadivi , Nader Karimi , Roshanak Roshandel , Shahram Shirani , Shadrokh Samavi

Training a small student network with the guidance of a larger teacher network is an effective way to promote the performance of the student. Despite the different types, the guided knowledge used to distill is always kept unchanged for…

Computer Vision and Pattern Recognition · Computer Science 2021-04-01 Jiangfan Han , Mengya Gao , Yujie Wang , Quanquan Li , Hongsheng Li , Xiaogang Wang

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small difference between training and test performance. Conventional wisdom attributes small generalization error either to properties of the…

Machine Learning · Computer Science 2017-02-28 Chiyuan Zhang , Samy Bengio , Moritz Hardt , Benjamin Recht , Oriol Vinyals

Large neural networks trained in the overparameterized regime are able to fit noise to zero train error. Recent work \citep{nakkiran2020distributional} has empirically observed that such networks behave as "conditional samplers" from the…

Machine Learning · Computer Science 2022-03-29 Gal Kaplun , Eran Malach , Preetum Nakkiran , Shai Shalev-Shwartz

We investigate the mechanisms of self-distillation in multi-class classification, particularly in the context of linear probing with fixed feature extractors where traditional feature learning explanations do not apply. Our theoretical…

Machine Learning · Computer Science 2025-02-20 Hyeonsu Jeong , Hye Won Chung

In self-supervised learning, self-distilled methods have shown impressive performance, learning representations useful for downstream tasks and even displaying emergent properties. However, state-of-the-art methods usually rely on ensembles…

Machine Learning · Computer Science 2026-05-01 Esteban Rodríguez-Betancourt , Edgar Casasola-Murillo

Although larger datasets are crucial for training large deep models, the rapid growth of dataset size has brought a significant challenge in terms of considerable training costs, which even results in prohibitive computational expenses.…

Computer Vision and Pattern Recognition · Computer Science 2025-08-06 Sheng-Feng Yu , Jia-Jiun Yao , Wei-Chen Chiu

Iterative generative models, such as noise conditional score networks and denoising diffusion probabilistic models, produce high quality samples by gradually denoising an initial noise vector. However, their denoising process has many…

Machine Learning · Computer Science 2021-01-08 Eric Luhman , Troy Luhman

Dataset distillation (DD) aims to minimize the time and memory consumption needed for training deep neural networks on large datasets, by creating a smaller synthetic dataset that has similar performance to that of the full real dataset.…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Xinhao Zhong , Bin Chen , Hao Fang , Xulin Gu , Shu-Tao Xia , En-Hui Yang

With the increasing size of datasets used for training neural networks, data pruning becomes an attractive field of research. However, most current data pruning algorithms are limited in their ability to preserve accuracy compared to models…

Computer Vision and Pattern Recognition · Computer Science 2024-08-15 Emanuel Ben-Baruch , Adam Botach , Igor Kviatkovsky , Manoj Aggarwal , Gérard Medioni

Modern deep learning models generalize remarkably well in-distribution, despite being overparametrized and trained with little to no explicit regularization. Instead, current theory credits implicit regularization imposed by the choice of…

Machine Learning · Computer Science 2026-03-17 Jonathan Wenger , Beau Coker , Juraj Marusic , John P. Cunningham

Unsupervised deep learning techniques are widely used to identify anomalous behaviour. The performance of such methods is a product of the amount of training data and the model size. However, the size is often a limiting factor for the…

Feature regression is a simple way to distill large neural network models to smaller ones. We show that with simple changes to the network architecture, regression can outperform more complex state-of-the-art approaches for knowledge…

Computer Vision and Pattern Recognition · Computer Science 2022-01-14 K L Navaneet , Soroush Abbasi Koohpayegani , Ajinkya Tejankar , Hamed Pirsiavash

The transfer of knowledge from one policy to another is an important tool in Deep Reinforcement Learning. This process, referred to as distillation, has been used to great success, for example, by enhancing the optimisation of agents,…

Deep learning techniques have been demonstrated to surpass preceding cutting-edge machine learning techniques in recent years, with computer vision being one of the most prominent examples. However, deep learning models suffer from…

Computer Vision and Pattern Recognition · Computer Science 2024-07-24 Gousia Habib , Tausifa jan Saleem , Sheikh Musa Kaleem , Tufail Rouf , Brejesh Lall

In this paper, we argue that mutual distillation between reinforcement learning policies serves as an implicit regularization, preventing them from overfitting to irrelevant features. We highlight two separate contributions: (i)…

Machine Learning · Computer Science 2025-09-25 Zhengpeng Xie , Jiahang Cao , Changwei Wang , Fan Yang , Marco Hutter , Qiang Zhang , Jianxiong Zhang , Renjing Xu

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

Knowledge distillation has proven to be an effective technique in improving the performance a student model using predictions from a teacher model. However, recent work has shown that gains in average efficiency are not uniform across…

Machine Learning · Computer Science 2022-06-15 Serena Wang , Harikrishna Narasimhan , Yichen Zhou , Sara Hooker , Michal Lukasik , Aditya Krishna Menon