AI Paper Atlas

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

Connecting Compression Spaces with Transformer for Approximate Nearest Neighbor Search

Haokui Zhang, Buzhou Tang, Wenze Hu, Xiaoyu Wang

ECCV 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Approximate nearest neighbor indexing · 5 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
compress features x4 for HNSW index buildingHNSW · GIST1Mindexing time (s): 733 -> 245Improved
compress features x4 for HNSW index buildingHNSW · Deep1Mindexing time (s): 300 -> 100Improved
compress features x4 for NSG index buildingNSG · GIST1Mindexing time (s): 1118 -> 645Improved
compress features x4 for HNSW index buildingHNSW · GIST1Mrecall 100@100: 94.39 -> 95.27Improved
compress features x2 for Bigann-1B indexHNSW · Bigann-1Bindexing time (h): 106 -> 51Improved
add CCST compression before PQ (60 bytes)PQ · GIST1Mrecall 1@1: 23.0 -> 39.5Improved
add CCST compression before PQ (32 bytes)PQ · Deep1Mrecall 1@1: 32.3 -> 53.3Improved
add CCST compression before L&C (60 bytes)L&C · GIST1Mrecall 1@1: 31.4 -> 30.7Mixed
use CCST instead of Catalyst for compression before PQ (16 bytes)PQ · Deep1Mrecall 1@1: 19.8 -> 32.5Improved
use CCST instead of VAE for compression x4HNSW · GIST1Mrecall 1@1: 49.2 -> 80.1Improved
add scalar quantization on top of CCST x4 (ablation)HNSW + CCST · GIST1Mrecall 100@100: 95.27 -> 91.42Hurt
add scalar quantization on top of CCST x4 (ablation)HNSW + CCST · GIST1Mindexing time (s): 245 -> 121Improved

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