Overview of the SISAP 2023 Indexing Challenge

Eric Sadit Tellez, Martin Aumüller, Edgar Chávez

Abstract: This manuscript presents the premiere SISAP 2023 Indexing Challenge, which seeks replicable and competitive solutions in the realm of approximate similarity search algorithms. Our aim is recall, all while optimizing build time, search time, and memory consumption. Using a subset of the deep features of a neural network model provided by the LAION-5B dataset, the challenge posed three tasks, each with its unique focus: Notably, an innovative and competitive binary mapping method emerged from the challenge. It also spotlighted graph methods as the preferred indexing technique for binary and real-valued high-dimensional vectors. However, these methods have little room for improvement. Enhancing memory efficiency, refining navigational strategies, and tackling the secondary memory challenge are pivotal next steps.