按年被提到
20162017 · 2 次2026
视觉、语音与图像生成›卷积网络与图像识别·arXiv:1606.02228 · cs.NE

Systematic evaluation of CNN advances on the ImageNet

Dmytro Mishkin, Nikolay Sergievskiy, Jiri Matas · 2016
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-05-06 · 最近 2017-12-03
2不同的人
2活跃月份
2讨论串
316被引(OpenAlex)
arXiv 摘要(候选层不写导读)

The paper systematically studies the impact of a range of recent advances in CNN architectures and learning methods on the object categorization (ILSVRC) problem. The evalution tests the influence of the following choices of the architecture: non-linearity (ReLU, ELU, maxout, compatibility with batch normalization), pooling variants (stochastic, max, average, mixed), network width, classifier design (convolutional, fully-connected, SPP), image pre-processing, and of learning parameters: learning rate, batch size, cleanliness of the data, etc. The performance gains of the proposed modifications are first tested individually and then in combination. The sum of individual gains is bigger than the observed improvement when all modifications are introduced, but the "deficit" is small suggesting independence of their benefits. We show that the use of 128x128 pixel images is sufficient to make qualitative conclusions about optimal network structure that hold for the full size Caffe and VGG nets. The results are obtained an order of magnitude faster than with the standard 224 pixel images.

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jph00 · 2017-05

“Changing to a different fixed color space is unlikely to help. However adding a learnable color space transformation is a great (and rarely known) trick. Both are discussed and compared in this terrific paper: https://arxiv.org/abs/1606.02228”

Sorting Two Tons of Lego, the Software Side原评论 ↗
被提交为 story · 1 次