NetVLAD

CNN‑based visual place recognition via VLAD descriptor aggregation.

NetVLAD is a CNN‑based visual place recognition model that aggregates dense local descriptors into a compact VLAD descriptor using a differentiable soft assignment to learned cluster centroids. Built on a VGG‑16 backbone, it produces a 32,768‑d L2‑normalized descriptor suitable for nearest‑neighbour place retrieval across images taken under varying conditions.