computer-vision-10
Image Instance Retrieval
3260 papers • 126 benchmarks • 313 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
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in image-instance-retrieval-10
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find image-instance-retrieval-10 models and implementations
Datasets
No datasets available.
Subtasks
Most implemented papers
Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval
Andrew Zisserman, Weidi Xie, Vicky Kalogeiton, A. Brown•Wed Jul 22 2020
Smooth-AP is a plug-and-play objective function that allows for end-to-end training of deep networks with a simple and elegant implementation and improves the performance over the state-of-the-art, especially for larger-scale datasets, thus demonstrating the effectiveness and scalability of Smooth-AP to real-world scenarios.
181