English
Related papers

Related papers: Test-time Batch Normalization

200 papers

Generative Adversarial Networks (GANs) significantly advanced image generation but their performance heavily depends on abundant training data. In scenarios with limited data, GANs often struggle with discriminator overfitting and unstable…

Machine Learning · Computer Science 2025-03-18 Yao Ni , Piotr Koniusz

Deep learning models face persistent challenges in training, particularly due to internal covariate shift and label shift. While single-mode normalization methods like Batch Normalization partially address these issues, they are constrained…

Machine Learning · Computer Science 2024-10-31 Bilal Faye , Hanane Azzag , Mustapha Lebbah , Djamel Bouchaffra

Deep neural networks (DNNs) are increasingly being used in autonomous systems. However, DNNs do not generalize well to domain shift. Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all…

Robotics · Computer Science 2025-09-04 Uddeshya Upadhyay

Training neural networks with batch normalization and weight decay has become a common practice in recent years. In this work, we show that their combined use may result in a surprising periodic behavior of optimization dynamics: the…

Machine Learning · Computer Science 2022-01-19 Ekaterina Lobacheva , Maxim Kodryan , Nadezhda Chirkova , Andrey Malinin , Dmitry Vetrov

Deep networks are prone to performance degradation when there is a domain shift between the source (training) data and target (test) data. Recent test-time adaptation methods update batch normalization layers of pre-trained source models…

Computer Vision and Pattern Recognition · Computer Science 2022-10-25 Wenyu Zhang , Li Shen , Wanyue Zhang , Chuan-Sheng Foo

Batch Normalization (BatchNorm) is a technique that improves the training of deep neural networks, especially Convolutional Neural Networks (CNN). It has been empirically demonstrated that BatchNorm increases performance, stability, and…

Machine Learning · Computer Science 2023-03-24 Yashna Peerthum , Mark Stamp

Deep learning has achieved tremendous success with independent and identically distributed (i.i.d.) data. However, the performance of neural networks often degenerates drastically when encountering out-of-distribution (OoD) data, i.e., when…

Machine Learning · Computer Science 2022-04-01 Nanyang Ye , Kaican Li , Haoyue Bai , Runpeng Yu , Lanqing Hong , Fengwei Zhou , Zhenguo Li , Jun Zhu

This work presents a novel training technique for deep neural networks that makes use of additional data from a distribution that is different from that of the original input data. This technique aims to reduce overfitting and improve the…

Computer Vision and Pattern Recognition · Computer Science 2020-06-09 Pravendra Singh , Pratik Mazumder , Vinay P. Namboodiri

Context: Deep Neural Networks (DNNs) are increasingly deployed in critical applications, where resilience against adversarial inputs is paramount. However, whether coverage-based or confidence-based, existing test prioritization methods…

Software Engineering · Computer Science 2025-09-30 Sheikh Md Mushfiqur Rahman , Nasir Eisty

Nowadays this is very popular to use deep architectures in machine learning. Deep Belief Networks (DBNs) are deep architectures that use stack of Restricted Boltzmann Machines (RBM) to create a powerful generative model using training data.…

Machine Learning · Computer Science 2015-08-21 Mohammad Ali Keyvanrad , Mohammad Mehdi Homayounpour

As one of the energy-efficient alternatives of conventional neural networks (CNNs), spiking neural networks (SNNs) have gained more and more interest recently. To train the deep models, some effective batch normalization (BN) techniques are…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Yufei Guo , Yuhan Zhang , Yuanpei Chen , Weihang Peng , Xiaode Liu , Liwen Zhang , Xuhui Huang , Zhe Ma

Distributed training of GNNs enables learning on massive graphs (e.g., social and e-commerce networks) that exceed the storage and computational capacity of a single machine. To reach performance comparable to centralized training,…

Machine Learning · Computer Science 2023-05-18 Jiong Zhu , Aishwarya Reganti , Edward Huang , Charles Dickens , Nikhil Rao , Karthik Subbian , Danai Koutra

Recent empirical studies have explored the idea of continuing to train a model at test-time for a given task, known as test-time training (TTT), and have found it to yield significant performance improvements. However, there is limited…

Machine Learning · Computer Science 2026-02-10 Jonas Hübotter , Patrik Wolf , Alexander Shevchenko , Dennis Jüni , Andreas Krause , Gil Kur

Research on generalization bounds for deep networks seeks to give ways to predict test error using just the training dataset and the network parameters. While generalization bounds can give many insights about architecture design, training…

Machine Learning · Computer Science 2022-03-21 Yi Zhang , Arushi Gupta , Nikunj Saunshi , Sanjeev Arora

Distribution shift severely degrades the performance of deep forecasting models. While this issue is well-studied for individual time series, it remains a significant challenge in the spatio-temporal domain. Effective solutions like…

Machine Learning · Computer Science 2026-04-20 Zhaobo Hu , Vincent Gauthier , Mehdi Naima

Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whether models are truly…

Machine Learning · Computer Science 2026-05-01 Henrik Voigt , Michael Habeck , Joachim Giesen

Transfer learning have been frequently used to improve deep neural network training through incorporating weights of pre-trained networks as the starting-point of optimization for regularization. While deep transfer learning can usually…

Machine Learning · Computer Science 2019-11-19 Ruosi Wan , Haoyi Xiong , Xingjian Li , Zhanxing Zhu , Jun Huan

As a promising distributed learning paradigm, federated learning (FL) involves training deep neural network (DNN) models at the network edge while protecting the privacy of the edge clients. To train a large-scale DNN model, batch…

Machine Learning · Computer Science 2023-11-10 Yanmeng Wang , Qingjiang Shi , Tsung-Hui Chang

Training a deep neural network (DNN) often involves stochastic optimization, which means each run will produce a different model. Several works suggest this variability is negligible when models have the same performance, which in the case…

Machine Learning · Statistics 2023-10-03 Sinjini Banerjee , Reilly Cannon , Tim Marrinan , Tony Chiang , Anand D. Sarwate

Recent works (e.g., (Li and Arora, 2020)) suggest that the use of popular normalization schemes (including Batch Normalization) in today's deep learning can move it far from a traditional optimization viewpoint, e.g., use of exponentially…

Machine Learning · Computer Science 2020-10-07 Zhiyuan Li , Kaifeng Lyu , Sanjeev Arora
‹ Prev 1 8 9 10 Next ›