Discovering Class-Specific Pixels for Weakly-Supervised Semantic Segmentation

Understand

We propose an approach to discover class-specific pixels for the weakly-supervised semantic segmentation task.

• We show that properly combining saliency and attention maps allows us to obtain reliable cues capable of significantly boosting the performance.
• First, we propose a simple yet powerful hierarchical approach to discover the class-agnostic salient regions, obtained using a salient object detector, which otherwise would be ignored.
• Second, we use fully convolutional attention maps to reliably localize the class-specific regions in a given image.