按年被提到
20162016 · 2 次2026
视觉、语音与图像生成›卷积网络与图像识别·arXiv:1605.07146 · cs.CV

Wide Residual Networks

Sergey Zagoruyko, Nikos Komodakis · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2016-05-24 · 最近 2016-06-01
2不同的人
2活跃月份
2讨论串
7,714被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Deep residual networks were shown to be able to scale up to thousands of layers and still have improving performance. However, each fraction of a percent of improved accuracy costs nearly doubling the number of layers, and so training very deep residual networks has a problem of diminishing feature reuse, which makes these networks very slow to train. To tackle these problems, in this paper we conduct a detailed experimental study on the architecture of ResNet blocks, based on which we propose a novel architecture where we decrease depth and increase width of residual networks. We call the resulting network structures wide residual networks (WRNs) and show that these are far superior over their commonly used thin and very deep counterparts. For example, we demonstrate that even a simple 16-layer-deep wide residual network outperforms in accuracy and efficiency all previous deep residual networks, including thousand-layer-deep networks, achieving new state-of-the-art results on CIFAR, SVHN, COCO, and significant improvements on ImageNet. Our code and models are available at https://github.com/szagoruyko/wide-residual-networks

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论vintermann · 2016-06

“Yup. An example from machine learning: This paper, "Weighted Residuals for Very Deep Networks" https://arxiv.org/abs/1605.08831 from May 28, cites this paper, "Wide Residual Networks" https://arxiv.org/abs/1605.07146 from May 23. Less than a week between them! And it's with good reason too, because they want to compare with state of the art on a certa…”

Simple Set Game Proof Stuns Mathematicians原评论 ↗
被提交为 story · 1 次