Two-Phase Learning for Weakly Supervised Object Localization

Understand

Weakly supervised semantic segmentation and localiza- tion have a problem of focusing only on the most important parts of an image since they use only image-level annota- tions.

• In this paper, we solve this problem fundamentally via two-phase learning.
• Our networks are trained in two steps.
• In the first step, a conventional fully convolutional network (FCN) is trained to find the most discriminative parts of an image.