arXiv-2017
随着深度学习技术的发展,CNN 在很多计算机视觉任务中崭露头角,但 increased representational power also comes increased probability of overfitting, leading to poor generalization.
为提升模型的泛化性能,模拟 object occlusion, 作者提出了 Cutout 数据增强的方法——randomly masking out square regions of input during training,take more of the image context into consideration when making decisions.
This technique encourages the network to better utilize the full context of the image, rather than relying on the presence of a small set of specific visual features(which may not always be present).
监督学习中提出 Cutout 数据增强方法(dropout 的一种形式,自监督中也有类似方法)
初始版:remove maximally activated features
最终版:随机中心点,正方形遮挡(可以在图片外,被图片边界截取后就不是正方形了)
使用时需要中心化一下(也即减去均值)
the dataset should be normalized about zero so that modified images will not have a large effect on the expected batch statistics.
评价指标为 top1 error
1)CIFAR10 and CIFAR100
单个实验都重复跑了5次,±x
下图探索 cutout 中不同 patch length 的影响,
2)STL-10
3)Analysis of Cutout’s Effect on Activations
引入 cutout 后浅层激活均有提升,深层 in the tail end of the distribution.
The latter observation illustrates that cutout is indeed encouraging the network to take into account a wider variety of features when making predictions, rather than relying on the presence of a smaller number of features
再聚焦下单个样本的
版权声明:本文内容由互联网用户自发贡献,该文观点仅代表作者本人。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容, 请发送邮件至 举报,一经查实,本站将立刻删除。