Image Instance Retrieval
1 papers with code • 0 benchmarks • 0 datasets
Image Instance Retrieval is the problem of retrieving images from a database representing the same object or scene as the one depicted in a query image.
Source: Compression of Deep Neural Networks for Image Instance Retrieval
Benchmarks
These leaderboards are used to track progress in Image Instance Retrieval
Most implemented papers
Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval
Andrew-Brown1/Smooth_AP
•
•
ECCV 2020
Optimising a ranking-based metric, such as Average Precision (AP), is notoriously challenging due to the fact that it is non-differentiable, and hence cannot be optimised directly using gradient-descent methods.
