AI Paper Atlas

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

The Group Loss++: A Deeper Look Into Group Loss for Deep Metric Learning

Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner, Sebastiano Vascon, Alessandro Torcinovich, Marcello Pelillo, Laura Leal-Taixé

TPAMI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 19 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 mixed pooling instead of average pooling (ablation)Group Loss · CUB-200-2011Recall@1: 65.5 -> 67.5Improved
add beta-normalization (ablation)Group Loss · CUB-200-2011Recall@1: 65.5 -> 66.8Improved
replace ReLU with LeakyReLU (ablation)Group Loss · CUB-200-2011Recall@1: 65.5 -> 61.3Hurt
replace ReLU with LeakyReLU (ablation)Group Loss · CARS196Recall@1: 85.6 -> 85.6No clear effect
add re-ranking (ablation)Group Loss · CUB-200-2011Recall@1: 65.5 -> 68.3Improved
add flip inference (ablation)Group Loss · CUB-200-2011Recall@1: 65.5 -> 68.0Improved
add all inference strategies cumulatively (Group Loss++) (ablation)Group Loss · CUB-200-2011Recall@1: 65.5 -> 72.6Improved
add all inference strategies cumulatively (Group Loss++) (ablation)Group Loss · CARS196Recall@1: 85.6 -> 90.4Improved
add all inference strategies cumulatively (Group Loss++) (ablation)Group Loss · In-Shop ClothesRecall@1: 86.8 -> 90.9Improved
add flip inference to mixed + beta + L + R (ablation)Group Loss++ · CUB-200-2011Recall@1: 70.2 -> 72.6Improved
add refinement steps (one step) over cross-entropy only (ablation)Group Loss · CUB-200-2011Recall@1: +0.6ppImproved
increase refinement steps to five (ablation)Group Loss · CARS196Recall@1: best at three or four stepsHurt

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