AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Improving Deep Metric Learning by Divide and Conquer

Artsiom Sanakoyeu, Pingchuan Ma, Vadim Tschernezki, Björn Ommer

TPAMI 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 22 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 progressive division instead of directly dividing into K_max clusters (ablation)Ours (fix) · SOPRecall@1: 78.67 -> 79.54Improved
cluster in the learned embedding space instead of random splits (ablation)Ours (fix) · SOPRecall@1: 71.99 -> 79.54Improved
cluster in the learned embedding space instead of random splits (ablation)Ours (fix) · CARS196Recall@1: 85.02 -> 86.46Improved
cluster in the learned embedding space instead of random splits (ablation)Ours (fix) · CUB200-2011Recall@1: 66.96 -> 68.43Improved
adaptive clustering instead of ground-truth super-category grouping (ablation)Ours (fix) · SOPRecall@1: 75.99 -> 79.54Improved
adaptive clustering instead of ground-truth super-category grouping (ablation)Ours (fix) · CUB200-2011Recall@1: 65.02 -> 68.43Improved
add separate subspaces per cluster (ablation)Ours (fix) · SOPRecall@1: 79.23 -> 79.54Improved
add separate subspaces per cluster (ablation)Ours (fix) · CARS196Recall@1: 83.90 -> 86.46Improved
add separate subspaces per cluster (ablation)Ours (fix) · In-shop ClothesRecall@1: 89.17 -> 90.15Improved
use learnable masks instead of fixed orthogonal masks (ablation)Ours (fix) · CARS196Recall@1: 86.46 -> 87.76Improved
use learnable masks instead of fixed orthogonal masks (ablation)Ours (fix) · CUB200-2011Recall@1: 68.43 -> 68.16No clear effect
increase K_max from 1 to 32 (ablation)Margin loss · SOPRecall@1: 77.11 -> 79.54Improved

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