Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

TL;DR

This paper improves image retrieval benchmarking by correcting annotations, introducing new protocols and challenging queries, and evaluating diverse methods on an enlarged dataset, revealing that the field remains unsolved.

Contribution

It provides revised annotations, new evaluation protocols, challenging queries, and a large distractor set for Oxford and Paris datasets, enabling fairer and more comprehensive benchmarking.

Findings

State-of-the-art methods still struggle with retrieval challenges.

Combining local features and CNNs yields the best results.

Image retrieval remains an open problem.

Abstract

In this paper we address issues with image retrieval benchmarking on standard and popular Oxford 5k and Paris 6k datasets. In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the reliability of the ground truth. Three new protocols of varying difficulty are introduced. The protocols allow fair comparison between different methods, including those using a dataset pre-processing stage. For each dataset, 15 new challenging queries are introduced. Finally, a new set of 1M hard, semi-automatically cleaned distractors is selected. An extensive comparison of the state-of-the-art methods is performed on the new benchmark. Different types of methods are evaluated, ranging from local-feature-based to modern CNN based methods. The best results are achieved by taking the best of the two worlds. Most importantly, image retrieval appears far from being solved.