本文介绍了一种从未标记图像数据中学习视觉特征的新方法，通过将图像划分为网格并打乱顺序，要求网络恢复原始配置，以此理解区域内和区域间的相互关系。实验表明，加入二元项可以提高拼图识别精度，并且3*3拼图优于2*2。尽管拼图识别准确率不高，但在迁移学习中表现优秀。
解决问题：
- Learning visual features from unlabeled image data
- a new approach in which the number of configurations can be arbitrarily large while the number of parameters remains
unchanged.
相关工作：
- 聚类；
- all images can be represented in a low-level space and trained encoders and/or decoders to recover the image and/or representation
Problem and Baseline Solution：
- an image is partitioned into a grid (e.g., 3*3) of patches and then disordered, and the task is to recover the original configuration.
- the network needs to understand what a patch contains as well as how two or more patches are related to each other
- we expect this task to teach a network both intra-patch and inter-patch information
Strategy
- 相对于9！的排列方式，作者提出新的算法
- u
最低0.47元/天 解锁文章
扫一扫
2149
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
