AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Differentiable Product Quantization for Memory Efficient Camera Relocalization

Zakaria Laskar, Iaroslav Melekhov, Assia Benbihi, Shuzhe Wang, Juho Kannala

ECCV 2024 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 10 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
add decoder trained with triplet loss instead of L2 loss (ablation)PQ4 + decoder · Aachen Day-Night nightaccuracy % (0.25m,2deg): 70.4 -> 79.6Improved
add differentiable PQ encoder (learned codebooks) (ablation)PQ4 · Aachen Day-Night nightaccuracy % (0.25m,2deg): 45.9 -> 68.4Improved
add D-PQED dequantization to PQ plus map compression at 1MBPQ4+Gamma · Aachen Day-Night nightaccuracy % (0.25m,2deg): 36.7 -> 77.6Improved
also quantize and dequantize query descriptors (symmetric setup) (ablation)D-PQED · Aachen Day-Night nightaccuracy % (0.25m,2deg): 81.6 -> 74.5Hurt
use N-pair loss instead of triplet loss (ablation)D-PQED · Aachen Day-Night nightaccuracy % (0.25m,2deg): 79.6 -> 76.5Hurt
use mutual nearest-neighbor matcher instead of SuperGlue (ablation)D-PQED · Aachen Day-Night nightaccuracy % (0.25m,2deg): 81.6 -> 38.8Hurt
balance PQ level M and map compression alpha at fixed memory (PQ4 vs PQ32 or PQ2) (ablation)PQ+Gamma+D-PQED · Aachen Day-Night night, 1MBaccuracy % (0.25m,2deg): PQ32 62.2, PQ4 77.6, PQ2 66.3Mixed
descriptor product quantization alone (PQ32) versus map compression at the same memory (ablation)PQ vs Gamma · Aachen Day-Night dayaccuracy % (0.25m,2deg): 83.9 -> 88.6Improved

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