What is pyramid pooling and how does PSPNet use it?

Updated May 15, 2026

Short answer

Pyramid pooling aggregates contextual information at multiple spatial scales for segmentation.

Deep explanation

PSPNet introduces Pyramid Pooling Module (PPM) to capture both local and global context by applying pooling at multiple grid scales (e.g., 1x1, 2x2, 3x3, 6x6). These pooled features are upsampled and concatenated with original feature maps. This helps the model understand both fine details and global scene layout.

Unlock with a Pro subscription to view this section.

View pricing

Real-world example

No real-world example available yet.

Unlock with a Pro subscription to view this section.

Upgrade to Pro

Common mistakes

No common mistakes listed yet.

Unlock with a Pro subscription to view this section.

Upgrade to Pro

Follow-up questions

No follow-up questions available yet.

Unlock with a Pro subscription to view this section.

Upgrade to Pro

More Computer Vision interview questions

View all →