BriefGPT.xyz
Oct, 2019
图像分类中有效数据增广的遮挡技术
Occlusions for Effective Data Augmentation in Image Classification
HTML
PDF
Ruth Fong, Andrea Vedaldi
TL;DR
通过批量数据增强技术中的遮盖作为数据增强手段,在高容量模型上(例如ResNet50)的图像分类任务中,为提高性能提供了一种简单的技术;同时,可以使用不同数量的遮挡来研究不同神经网络架构的鲁棒性。
Abstract
deep networks
for
visual recognition
are known to leverage "easy to recognise" portions of objects such as faces and distinctive texture patterns. The lack of a holistic understanding of objects may increase frag
→