Nicholas Hopper

Reciprocal Rank Fusion

Nicholas Hopper has used Reciprocal Rank Fusion in his work at Memector.

Where Nicholas Hopper has used Reciprocal Rank Fusion

  • Searches 1,859 templates by fusing CLIP text-to-image, MiniLM text, Postgres keyword search and two sketch channels with Reciprocal Rank Fusion.

    Memector

  • Raised candidate depth per channel from 80 to 150 after finding that a result one place past a channel's cutoff scored zero there, which moved recall@5 from 98% to 100%.

    Memector