Not All Pixels Are Equal: Learning Pixel Hardness for Semantic Segmentation

Understand

Semantic segmentation has recently witnessed great progress.

• Despite the impressive overall results, the segmentation performance in some hard areas (e.g., small objects or thin parts) is still not promising.
• A straightforward solution is hard sample mining, which is widely used in object detection.
• Yet, most existing hard pixel mining strategies for semantic segmentation often rely on pixel's loss value, which tends to decrease during training.