AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Deep Supervised Hashing With Anchor Graph

Yudong Chen, Zhihui Lai, Yujuan Ding, Kaiyi Lin, Wai Keung Wong

ICCV 2019 · Graph learning › Graph algorithms and clustering · approach: Graph distance and retrieval · 66 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
obtain training codes directly from Algorithm 1 instead of the network output (DAGH-2 vs DAGH-1) (ablation)DAGH · CIFAR-10, 12 bitsMAP: 0.881 -> 0.934Improved
obtain training codes directly from Algorithm 1 instead of the network output (DAGH-2 vs DAGH-1) (ablation)DAGH · Fashion-MNIST, 12 bitsMAP: 0.870 -> 0.932Improved
obtain training codes directly from Algorithm 1 instead of the network output (DAGH-2 vs DAGH-1) (ablation)DAGH · NUS-WIDE, 12 bitsMAP: 0.707 -> 0.760Improved
add the deep hashing term R2 to the regression term R1 (ablation)DAGH · NUS-WIDE, 12 bitsMAP: 0.739 -> 0.772Improved
add the deep hashing term R2 to the regression term R1 (ablation)DAGH · NUS-WIDE, 48 bitsMAP: 0.762 -> 0.787Improved
add the discriminative code term R3 to the regression term R1 (ablation)DAGH · NUS-WIDE, 12 bitsMAP: 0.739 -> 0.740No clear effect
add the discriminative code term R3 to the regression term R1 (ablation)DAGH · NUS-WIDE, 48 bitsMAP: 0.762 -> 0.790Improved
add R3 on top of R1+R2 (ablation)DAGH · NUS-WIDE, 12 bitsMAP: 0.772 -> 0.760Hurt
add R3 on top of R1+R2 (ablation)DAGH · NUS-WIDE, 48 bitsMAP: 0.787 -> 0.802Improved
train DPSH on all training samples instead of a 5,000-image subsetDPSH · CIFAR-10, 12 bitsMAP: 0.661 -> 0.925 (time 58.5m -> 842.3m)Improved
train DSDH on all training samples instead of a subsetDSDH · CIFAR-10, 12 bitsMAP: 0.735 -> 0.931 (time 58.9m -> 846.1m)Improved
vary the number of anchors (ablation)DAGH · CIFAR-10MAPNo 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