Search Results for author:
Found 1 papers, 1 papers with code
AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift
Our result credits the best accuracy to the ResNet-101 model pre-trained on the Landmarks dataset for both verification and retrieval tasks by 84% and 24%, respectively.
Ranked #1 on
Image Classification
on AmsterTime
(using extra training data)
Cannot find the paper you are looking for? You can
Submit a new open access paper.
