AI Paper Atlas

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

DiVA: Diverse Visual Feature Aggregation for Deep Metric Learning

Timo Milbich, Karsten Roth, Homanga Bharadhwaj, Samarth Sinha, Yoshua Bengio, Björn Ommer, Joseph Paul Cohen

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 64 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 all four tasks (shared, intra-class, DaNCE) to margin-loss discriminative training (ablation)Margin loss, Inception-BN · CUB200-2011Recall@1: 63.6 -> 66.4Improved
add all four tasks (ablation)Margin loss, Inception-BN · CARS196Recall@1: 79.4 -> 83.1Improved
add all four tasks (ablation)Margin loss, Inception-BN · SOPRecall@1: 76.6 -> 77.5Improved
add the intra-class task to D & Da & S (ablation)DiVA, Inception-BN · CARS196Recall@1: 82.6 -> 83.1Improved
add the shared task to D & Da & I (ablation)DiVA, Inception-BN · SOPRecall@1: 75.8 -> 77.5Improved
add embedding decorrelation between tasks (ablation)DiVA, Inception-BN · CUB200-2011Recall@1: 65.6 -> 66.4Improved
share the feature encoder across tasks instead of training separate models (ablation)DiVA · CUB200-2011Recall@1: 48.7 -> 66.4Improved
use multiple diverse tasks without decorrelation versus margin baseline (ablation)margin loss baseline · CUB200-2011Recall@1: 63.6 -> 65.6Improved
use distance-adapted NCE (DaNCE) instead of standard NCE as extra task (ablation)discriminative DML · CUB200-2011 (Inception-BN)Recall@1Improved
add standard NCE as extra task to discriminative DML (ablation)discriminative DML · CUB200-2011 (Inception-BN)Recall@1Hurt
add DeepCluster, RotNet or Instance Discrimination self-supervision to discriminative DML (ablation)discriminative DML · CUB200-2011 (Inception-BN)Recall@1No clear effect
learn the temperature parameter tau in NCE (ablation)DaNCE · DML benchmarksRecall@1No clear effect

Later papers that compared with this method

8 later accepted papers report DIVA as a baseline in their results tables; 8 of them report a better number on most of the results they share with it.

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