图 书 馆
可视化和理解卷积网络13th European Conference on Computer Vision (ECCV), Zurich 2014 |
|
| 课程网址: | http://videolectures.net/eccv2014_zeiler_convolutional_networks/ |
| 主讲教师: | Matthew Zeiler |
| 开课单位: | 纽约大学 |
| 开课时间: | 2014-10-29 |
| 课程语种: | 英语 |
| 中文简介: |  大型卷积网络模型最近在ImageNet基准Krizhevsky等人身上展示了令人印象深刻的分类性能。 [18]。但是，对于为什么它们表现如此出色或如何进行改进尚无明确的了解。在本文中，我们将探讨这两个问题。我们介绍了一种新颖的可视化技术，可深入了解中间要素层的功能和分类器的操作。在诊断角色中使用时，这些可视化使我们能够找到在ImageNet分类基准上胜过Krizhevsky等人的模型架构。我们还进行了消融研究，以发现不同模型层对性能的贡献。我们展示了ImageNet模型可以很好地推广到其他数据集：重新训练softmax分类器时，它令人信服地击败了Caltech 101和Caltech 256数据集上的最新技术成果。 |
| 课程简介: | Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark Krizhevsky et al. [18]. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we explore both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. Used in a diagnostic role, these visualizations allow us to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark. We also perform an ablation study to discover the performance contribution from different model layers. We show our ImageNet model generalizes well to other datasets: when the softmax classifier is retrained, it convincingly beats the current state-of-the-art results on Caltech-101 and Caltech-256 datasets. |
| 关 键 词: | 计算机视觉; 可视化技术; ImageNet分类 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-06-11：吴淑曼 |
| 最后编审: | 2020-06-15：吴淑曼(课程编辑志愿者) |
| 阅读次数: | 37 |