AI Paper Atlas

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

Deep Metric Learning with Spherical Embedding

Dingyi Zhang, Yingming Li, Zhongfei Zhang

NeurIPS 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 16 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 SEC to Multi-Similarity lossDeep metric learning · CUB200-2011R@1: 66.14 -> 68.79Improved
Add SEC to Multi-Similarity lossDeep metric learning · Cars196R@1: 84.07 -> 85.73Improved
Add SEC to Multi-Similarity lossDeep metric learning · SOPR@1: 76.29 -> 78.67Improved
Add SEC to Multi-Similarity lossDeep metric learning · In-ShopR@1: 88.11 -> 89.87Improved
Add SEC to CosfaceFace recognition · MegaFace Challenge 1 ($10^6$ distractors)rank-1 accuracy: 90.71 -> 91.13Improved
Add SEC to NT-XentSimCLR · CIFAR-10, 100 epochstop-1 linear evaluation accuracy: 84.76 -> 86.87Improved
Add SEC to NT-XentSimCLR · CIFAR-100, 100 epochstop-1 linear evaluation accuracy: 58.43 -> 61.66Improved
Use EMA to update SEC's target norm (ρ=0.01) (ablation)Triplet Loss + SEC · Cars196R@1: 67.89 -> 74.57Improved
Set SEC weight η to 0.1 (ablation)Triplet Loss + SEC · Cars196R@1: 60.79 -> 66.72Improved
Set SEC weight η to 0.5 (ablation)Triplet Loss + SEC · Cars196R@1: 60.79 -> 67.89Improved
Increase SEC weight η to 1.5 (ablation)Triplet Loss + SEC · Cars196R@1: 67.89 -> 57.72Hurt
Replace SEC with L²-reg (ablation)Triplet Loss · Cars196R@1: 67.89 -> 63.02Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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