Efficient Nearest Neighbors Search for Large-Scale Landmark Recognition
This addresses the computational bottleneck in large-scale retrieval for landmark recognition, offering a practical solution for applications requiring fast and accurate searches.
The paper tackles the problem of efficient nearest neighbor search for large-scale landmark recognition by proposing a novel multi-index hashing method called Bag of Indexes (BoI), which drastically reduces query time and outperforms state-of-the-art accuracy on datasets like Holidays+Flickr1M, Oxford105k, and Paris106k.
The problem of landmark recognition has achieved excellent results in small-scale datasets. When dealing with large-scale retrieval, issues that were irrelevant with small amount of data, quickly become fundamental for an efficient retrieval phase. In particular, computational time needs to be kept as low as possible, whilst the retrieval accuracy has to be preserved as much as possible. In this paper we propose a novel multi-index hashing method called Bag of Indexes (BoI) for Approximate Nearest Neighbors (ANN) search. It allows to drastically reduce the query time and outperforms the accuracy results compared to the state-of-the-art methods for large-scale landmark recognition. It has been demonstrated that this family of algorithms can be applied on different embedding techniques like VLAD and R-MAC obtaining excellent results in very short times on different public datasets: Holidays+Flickr1M, Oxford105k and Paris106k.