AI Paper Atlas

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

Deep Metric Learning with Hierarchical Triplet Loss

Weifeng Ge

ECCV 2018 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 475 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 anchor-neighbor sampling (ablation)triplet loss with semi-hard mining · In-Shop Clothes RetrievalRecall@1 (%): 62.3 -> 75.3Improved
add anchor-neighbor sampling (ablation)triplet loss with semi-hard mining · CUB-200-2011Recall@1 (%): 55.9 -> 56.4Improved
add dynamic violate margin with flat class tree (ablation)triplet loss with A-N sampling · In-Shop Clothes RetrievalRecall@1 (%): 75.3 -> 78.9Improved
use hierarchical tree of depth 16 instead of flat tree (ablation)HTL · In-Shop Clothes RetrievalRecall@1 (%): 78.9 -> 80.9Improved
increase tree depth from 16 to 32 (ablation)HTL · In-Shop Clothes RetrievalRecall@1 (%): 80.9 -> 79.3Hurt
use tree depth 16 instead of depth 8 (ablation)HTL · In-Shop Clothes RetrievalRecall@1 (%): 78.7 -> 80.9Improved
add hierarchical tree (depth 16) over flat tree (ablation)HTL · CUB-200-2011Recall@1 (%): 56.0 -> 57.1Improved
add A-N sampling and dynamic violate margin (ablation)HDC contrastive loss · In-Shop Clothes RetrievalRecall@1 (%): 62.1 -> 69.4Improved
add A-N sampling and dynamic violate margin (ablation)HDC contrastive loss · CUB-200-2011Recall@1 (%): 53.6 -> 54.1Improved
use hard negative mining instead of random sampling (ablation)triplet loss · In-Shop Clothes RetrievalRecall@1 (%): 59.3 -> 60.1No clear effect
use semi-hard instead of hard negative mining (ablation)triplet loss · In-Shop Clothes RetrievalRecall@1 (%): 60.1 -> 62.3Improved
replace triplet loss with HTLtriplet loss baseline · Cars-196Recall@1 (%): 79.2 -> 81.4Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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