AI Paper Atlas

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

SoftTriple Loss: Deep Metric Learning Without Triplet Sampling

Qi Qian, Lei Shang, Baigui Sun, Juhua Hu, Hao Li, Rong Jin

ICCV 2019 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 427 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 multiple centers per class (K=10) instead of one center (SoftMax_norm) (ablation)SoftTriple · CUB-2011 (64-d)Recall@1: 57.8 -> 60.1Improved
use multiple centers per class (K=10) instead of one center (SoftMax_norm) (ablation)SoftTriple · CUB-2011 (large embeddings)Recall@1: 64.2 -> 65.4Improved
use multiple centers per class (K=10) instead of one center (SoftMax_norm) (ablation)SoftTriple · Cars196 (64-d)Recall@1: 76.8 -> 78.6Improved
use multiple centers per class (K=10) instead of one center (SoftMax_norm) (ablation)SoftTriple · Cars196 (large embeddings)Recall@1: 83.2 -> 84.5Improved
increase centers from 1 to 2 (K=2, no regularizer) (ablation)SoftTriple · SOP (64-d)Recall@1: 75.9 -> 76.3Improved
use multiple centers instead of one center (ablation)SoftTriple · SOP (large embeddings)Recall@1: 78.0 -> 78.3Improved
replace ProxyNCA with normalized SoftMax lossSoftMax_norm · Cars196 (64-d)Recall@1: 73.2 -> 76.8Improved
replace ProxyNCA with normalized SoftMax lossSoftMax_norm · SOP (64-d)Recall@1: 73.7 -> 75.9Improved
increase number of centers from 1 to 10 (ablation)SoftTriple with regularizer · CUB-2011Recall@1Improved
increase number of centers beyond 10 with the regularizer (ablation)SoftTriple with regularizer · CUB-2011Recall@1No clear effect
add the L2,1 center-merging regularizer when centers are over-parameterized (ablation)SoftTriple · CUB-2011 (K=20)Recall@1Improved
add the regularizer to shrink similar centers (ablation)SoftTriple · CUB-2011 (K=20)number of unique centers per classImproved

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