Learning Query Expansion over the Nearest Neighbor Graph
This work addresses the problem of enhancing retrieval accuracy for image search applications, representing an incremental improvement over existing query expansion methods.
The paper tackles the problem of improving retrieval metrics in image search by proposing Graph Query Expansion (GQE), a hierarchical model that learns to aggregate information over an extended neighborhood of the query using the nearest neighbors graph, achieving state-of-the-art results on known benchmarks.
Query Expansion (QE) is a well established method for improving retrieval metrics in image search applications. When using QE, the search is conducted on a new query vector, constructed using an aggregation function over the query and images from the database. Recent works gave rise to QE techniques in which the aggregation function is learned, whereas previous techniques were based on hand-crafted aggregation functions, e.g., taking the mean of the query's nearest neighbors. However, most QE methods have focused on aggregation functions that work directly over the query and its immediate nearest neighbors. In this work, a hierarchical model, Graph Query Expansion (GQE), is presented, which is learned in a supervised manner and performs aggregation over an extended neighborhood of the query, thus increasing the information used from the database when computing the query expansion, and using the structure of the nearest neighbors graph. The technique achieves state-of-the-art results over known benchmarks.