FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference

Understand

The main obstacle to weakly supervised semantic image segmentation is the difficulty of obtaining pixel-level information from coarse image-level annotations.

• Most methods based on image-level annotations use localization maps obtained from the classifier, but these only focus on the small discriminative parts of objects and do not capture precise boundaries.
• FickleNet explores diverse combinations of locations on feature maps created by generic deep neural networks.
• It selects hidden units randomly and then uses them to obtain activation scores for image classification.