AI Paper Atlas

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

Hard negative examples are hard, but useful

Hong Xuan, Abby Stylianou, Xiaotong Liu, Robert Pless

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 145 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 hard negative mining with standard triplet loss (HN) instead of SCT (ablation)triplet loss with hard negative mining · CUB, CAR, Hotels-50K (high hard-triplet ratio early in training)training convergenceHurt
add selectively contrastive triplet loss (SCT) in place of semi-hard negative mining (SHN)triplet loss with hard negative mining · Hotels-50KRecall@1Improved
add SCT in place of SHNtriplet loss with hard negative mining · CUB, CAR, SOP, In-shop ClothRecall@1Improved
add SCT instead of SHN, which only weakly separates hard negativestriplet loss with hard negative mining · CUB and CAR triplet diagramhard negative separationImproved
add SCT instead of SHN for unseen-class generalizationtriplet loss with hard negative mining · CAR (unseen test classes)anchor-positive similarity on test classesImproved
add SCT loss at the margin-based formulation instead of NCA-based (ablation)triplet loss · numerical simulation of gradient updateproblematic region behaviorNo clear effect

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