English
Related papers

Related papers: High-Rate Mixout: Revisiting Mixout for Robust Dom…

200 papers

Dropout is used to avoid overfitting by randomly dropping units from the neural networks during training. Inspired by dropout, this paper presents GI-Dropout, a novel dropout method integrating with global information to improve neural…

Computation and Language · Computer Science 2018-10-11 Hengru Xu , Shen Li , Renfen Hu , Si Li , Sheng Gao

Overfitting is a well-known issue extending even to state-of-the-art (SOTA) Machine Learning (ML) models, resulting in reduced generalization, and a significant train-test performance gap. Mitigation measures include a combination of…

Machine Learning · Computer Science 2025-05-29 Shreyas Gururaj , Lars Grüne , Wojciech Samek , Sebastian Lapuschkin , Leander Weber

Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks. However, data augmentation is rarely considered for point cloud processing despite many…

Computer Vision and Pattern Recognition · Computer Science 2021-03-11 Dogyoon Lee , Jaeha Lee , Junhyeop Lee , Hyeongmin Lee , Minhyeok Lee , Sungmin Woo , Sangyoun Lee

Deep convolutional neural networks have shown remarkable performance on various computer vision tasks, and yet, they are susceptible to picking up spurious correlations from the training signal. So called `shortcuts' can occur during…

Computer Vision and Pattern Recognition · Computer Science 2022-09-21 Mobarakol Islam , Ben Glocker

The paper presents a novel, principled approach to train recurrent neural networks from the Reservoir Computing family that are robust to missing part of the input features at prediction time. By building on the ensembling properties of…

Machine Learning · Computer Science 2017-05-09 Davide Bacciu , Francesco Crecchi , Davide Morelli

Ensemble methods are known for enhancing the accuracy and robustness of machine learning models by combining multiple base learners. However, standard approaches like greedy or random ensembling often fall short, as they assume a constant…

Machine Learning · Computer Science 2025-06-24 Sebastian Pineda Arango , Maciej Janowski , Lennart Purucker , Arber Zela , Frank Hutter , Josif Grabocka

Dropout as a common regularizer to prevent overfitting in deep neural networks has been less effective in convolutional layers than in fully connected layers. This is because Dropout drops features randomly, without considering local…

Machine Learning · Computer Science 2025-06-05 Liyan Chen , Philippos Mordohai , Sergul Aydore

Mixup provides interpolated training samples and allows the model to obtain smoother decision boundaries for better generalization. The idea can be naturally applied to the domain adaptation task, where we can mix the source and target…

Computer Vision and Pattern Recognition · Computer Science 2023-03-20 Daehan Kim , Minseok Seo , Kwanyong Park , Inkyu Shin , Sanghyun Woo , In-So Kweon , Dong-Geol Choi

Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded…

Machine Learning · Statistics 2016-10-05 Yarin Gal , Zoubin Ghahramani

In this paper, we have investigated recurrent deep neural networks (DNNs) in combination with regularization techniques as dropout, zoneout, and regularization post-layer. As a benchmark, we chose the TIMIT phone recognition task due to its…

Computation and Language · Computer Science 2018-06-20 Jan Vanek , Josef Michalek , Josef Psutka

Bayesian Inference offers principled tools to tackle many critical problems with modern neural networks such as poor calibration and generalization, and data inefficiency. However, scaling Bayesian inference to large architectures is…

Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in pooling layers is still not clear. This paper demonstrates…

Machine Learning · Computer Science 2015-12-07 Haibing Wu , Xiaodong Gu

Existing pretraining data mixing methods for large language models (LLMs) typically follow a domain-wise methodology, a top-down process that first determines domain weights and then performs uniform data sampling across each domain.…

Computation and Language · Computer Science 2025-03-04 Xiangyu Xi , Deyang Kong , Jian Yang , Jiawei Yang , Zhengyu Chen , Wei Wang , Jingang Wang , Xunliang Cai , Shikun Zhang , Wei Ye

Though convolutional neural networks (CNNs) have demonstrated remarkable ability in learning discriminative features, they often generalize poorly to unseen domains. Domain generalization aims to address this problem by learning from a set…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Kaiyang Zhou , Yongxin Yang , Yu Qiao , Tao Xiang

Deep neural networks often work well when they are over-parameterized and trained with a massive amount of noise and regularization, such as weight decay and dropout. Although dropout is widely used as a regularization technique for fully…

Computer Vision and Pattern Recognition · Computer Science 2018-10-31 Golnaz Ghiasi , Tsung-Yi Lin , Quoc V. Le

The generalization power of the pre-trained model is the key for few-shot deep learning. Dropout is a regularization technique used in traditional deep learning methods. In this paper, we explore the power of dropout on few-shot learning…

Computer Vision and Pattern Recognition · Computer Science 2023-01-27 Shaobo Lin , Xingyu Zeng , Rui Zhao

Deep networks have achieved impressive results on a range of well-curated benchmark datasets. Surprisingly, their performance remains sensitive to perturbations that have little effect on human performance. In this work, we propose a novel…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Jonas Ngnawe , Marianne Abemgnigni Njifon , Jonathan Heek , Yann Dauphin

Deep ensembles are a powerful tool in machine learning, improving both model performance and uncertainty calibration. While ensembles are typically formed by training and tuning models individually, evidence suggests that jointly tuning the…

Machine Learning · Computer Science 2025-11-10 Laurits Fredsgaard , Mikkel N. Schmidt

Among the most successful methods for sparsifying deep (neural) networks are those that adaptively mask the network weights throughout training. By examining this masking, or dropout, in the linear case, we uncover a duality between such…

Machine Learning · Computer Science 2022-01-04 Daniel LeJeune , Hamid Javadi , Richard G. Baraniuk

State-of-the-art computer vision models are rapidly increasing in capacity, where the number of parameters far exceeds the number required to fit the training set. This results in better optimization and generalization performance. However,…

Machine Learning · Computer Science 2020-09-24 Najeeb Khan , Ian Stavness