FPN (Feature Pyramid Network) is a neural network architecture that constructs a feature pyramid from a single input image, enabling efficient detection of objects at multiple scales. It combines high-resolution low-level features (for small objects) with low-resolution high-level features (for large objects) via top-down pathways and lateral connections. FPN is a core component in modern object detectors like Faster R-CNN and RetinaNet, enhancing accuracy in diverse vision tasks.
