Papers › Hard negative examples are hard, but useful

Hard negative examples are hard, but useful

24 Jul 2020ECCV 2020 8arXiv:2007.12749archive 2025-07-28

Hong Xuan, Abby Stylianou, Xiaotong Liu, Robert Pless

Triplet loss is an extremely common approach to distance metric learning. Representations of images from the same class are optimized to be mapped closer together in an embedding space than representations of images from different classes. Much work on triplet losses focuses on selecting the most useful triplets of images to consider, with strategies that select dissimilar examples from the same class or similar examples from different classes. The consensus of previous research is that optimizing with the \textit{hardest} negative examples leads to bad training behavior. That's a problem -- these hardest negatives are literally the cases where the distance metric fails to capture semantic similarity. In this paper, we characterize the space of triplets and derive why hard negatives make triplet loss training fail. We offer a simple fix to the loss function and show that, with this fix, optimizing with hard negative examples becomes feasible. This leads to more generalizable features, and image retrieval results that outperform state of the art for datasets with high intra-class variance.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

littleredxh/HardNegative officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Image RetrievalMetric LearningRetrievalSemantic SimilaritySemantic Textual Similarity

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Metric Learning CARS196 SCT(64) R@1 73.2 #36 of 36 Archive leaderboard report
Metric Learning CUB-200-2011 SCT(64) R@1 57.7 #28 of 30 Archive leaderboard report
Metric Learning In-Shop SCT(512) R@1 90 #14 of 15 Archive leaderboard report
Metric Learning Stanford Online Products SCT(512) R@1 81.6 #14 of 33 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Triplet Loss

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections