AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Efficient Querying from Weighted Binary Codes

Zhenyu Weng, Yuesheng Zhu

AAAI 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Locality-sensitive hashing · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use weighted-distance-ordered bucket search with multi-index tables and exact candidate merging instead of linear scanningWeighted binary-code querying on Places205, GIST1M, and SIFT1B · Places205, GIST1M, and SIFT1Bprecision@K: 25.29 vs 25.29; 13.20 vs 13.20; 3.25 vs 3.25 (MIWQ vs Linear Scan, 32-bit 1-NN)No clear effect
Use weighted-distance-ordered bucket search with multi-index tables and exact candidate merging instead of linear scanningWeighted binary-code querying on SIFT1B · SIFT1B (32-bit, 1-NN)speed-up factor: 1.0 -> 3639.0Improved
Use exact weighted-distance candidate selection rather than MIH's Hamming-based candidate filteringMIWQ vs MIH · SIFT1B (64-bit, 100-NN)precision (%): 10.52 -> 14.13Improved
Use MIWQ rather than MIHSIFT1B (64-bit, 100-NN) · SIFT1B (64-bit, 100-NN)speed-up factor: 1899.9 -> 1356.0Hurt
Use the proposed table-merging algorithm rather than PQTable's merging algorithmPQTable with max-heap merging · SIFT1B (32-bit, 1-NN)query time (ms): 50.44 -> 6.15Improved
Use MIWQ's bucket-finding process rather than PQTable'sExact weighted binary-code search · SIFT1B (32-bit, 1-NN)query time (ms): 50.44 -> 6.15Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy