Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Nam, Giung"'
Autor:
Nam, Giung, Lee, Juho
While ensembling deep neural networks has shown promise in improving generalization performance, scaling current ensemble methods for large models remains challenging. Given that recent progress in deep learning is largely driven by the scale, exempl
Externí odkaz:
http://arxiv.org/abs/2411.14860
Large-scale contrastive vision-language pre-trained models provide the zero-shot model achieving competitive performance across a range of image classification tasks without requiring training on downstream data. Recent works have confirmed that whil
Externí odkaz:
http://arxiv.org/abs/2404.00860
Transfer learning has recently shown significant performance across various tasks involving deep neural networks. In these transfer learning scenarios, the prior distribution for downstream data becomes crucial in Bayesian model averaging (BMA). Whil
Externí odkaz:
http://arxiv.org/abs/2403.07282
Deep ensemble is a simple yet powerful way to improve the performance of deep neural networks. Under this motivation, recent works on mode connectivity have shown that parameters of ensembles are connected by low-loss subspaces, and one can efficient
Externí odkaz:
http://arxiv.org/abs/2306.11304
Given the ever-increasing size of modern neural networks, the significance of sparse architectures has surged due to their accelerated inference speeds and minimal memory demands. When it comes to global pruning techniques, Iterative Magnitude Prunin
Externí odkaz:
http://arxiv.org/abs/2305.14852
A Neural Process (NP) estimates a stochastic process implicitly defined with neural networks given a stream of data, rather than pre-specifying priors already known, such as Gaussian processes. An ideal NP would learn everything from data without any
Externí odkaz:
http://arxiv.org/abs/2304.09431
Decoupling representation learning and classifier learning has been shown to be effective in classification with long-tailed data. There are two main ingredients in constructing a decoupled learning scheme; 1) how to train the feature extractor for r
Externí odkaz:
http://arxiv.org/abs/2304.09426
Ensembles of deep neural networks have demonstrated superior performance, but their heavy computational cost hinders applying them for resource-limited environments. It motivates distilling knowledge from the ensemble teacher into a smaller student n
Externí odkaz:
http://arxiv.org/abs/2206.15047
Deep ensembles excel in large-scale image classification tasks both in terms of prediction accuracy and calibration. Despite being simple to train, the computation and memory cost of deep ensembles limits their practicability. While some recent works
Externí odkaz:
http://arxiv.org/abs/2110.14149
Given the ever-increasing size of modern neural networks, the significance of sparse architectures has surged due to their accelerated inference speeds and minimal memory demands. When it comes to global pruning techniques, Iterative Magnitude Prunin
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b2db2c56bbfc337f54ffde890d788b33
http://arxiv.org/abs/2305.14852
http://arxiv.org/abs/2305.14852