Two-Phase Learning for Weakly Supervised Object Localization

最新推荐文章于 2023-07-27 15:35:07 发布

weixin_30325071

最新推荐文章于 2023-07-27 15:35:07 发布

阅读量178

点赞数

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/everyday-haoguo/p/Two-Phase.html

本文提出了一种新颖的方法来解决弱监督语义分割及定位中存在的仅关注图像最重要部分的问题。通过两阶段训练过程，首先定位最判别性的区域，然后屏蔽该区域，继续寻找次重要的部分，以此类推，直至覆盖整个目标。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Background

1. Weakly supervised semantic segmentation and localization have a problem of focus only on the most important parts of an image since they use only image-level annotations.

2. The complete extent of objects are good for object localization.

3. A novel method is proposed to cover the entire parts of objects.

Main points

To cover the entire parts of objects, a simple way is to find the most discriminative part, the second most discriminative part and so on. When locating the second most discriminative part, we mask out the most discriminative one. This is the core idea of this paper.

1. Find the most discriminative parts of an image as usual, which is done by the first network.

2. Mask out the most discriminative parts of an image.

3. Train the same network to find the second most discriminatvie parts.

Drawbacks

1. The network is not shared during two-phase learning.

2. The network can not be trained in an end-to-end manner.

转载于:https://www.cnblogs.com/everyday-haoguo/p/Two-Phase.html