AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Relaxation-Free Deep Hashing via Policy Gradient

Xin Yuan, Liangliang Ren, Jiwen Lu, Jie Zhou

ECCV 2018 · Reinforcement learning › Policy gradient and actor-critic · approach: Alternative policy update rules · 44 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
replace continuous relaxation (HashNet) with policy-gradient binary samplingHashNet · CIFAR-10 (64-bit)MAP: 73.9 -> 76.2Improved
replace relaxation with policy gradientHashNet · NUS-WIDE (64-bit)MAP: 77.6 -> 79.2Improved
replace relaxation with policy gradientHashNet · ImageNet (64-bit)MAP: 68.4 -> 71.6Improved
use weighted reward beta=0.5 instead of beta=0.1 (ablation)PGDH · CIFAR-10 (64-bit)MAP: 10.12 -> 73.65Improved
use weighted reward beta=0.5 instead of beta=0.1 (ablation)PGDH · NUS-WIDE (64-bit)MAP: 31.32 -> 77.95Improved
use weighted reward beta=0.7 instead of beta=0.1 (ablation)PGDH · ImageNet (64-bit)MAP: 1.14 -> 70.32Improved
use beta=0.8 instead of beta=0.9 (ablation)PGDH · CIFAR-10 (64-bit)MAP: 34.12 -> 75.12Improved
increase Monte Carlo samples T (ablation)PGDH · CIFAR-10MAP: MAP degrades at small T and saturates for larger TMixed
update codebook every iteration (R=1) instead of R=5 (ablation)PGDH · CIFAR-10 (64-bit)MAP: MAP very low during trainingHurt
update codebook once per epoch (R=40) instead of R=5 (ablation)PGDH · CIFAR-10 (64-bit)MAP: MAP rises very slowlyHurt
stochastic instead of deterministic code generation at test (ablation)PGDH · CIFAR-10 (64-bit)MAP: 75.54 -> 75.21No clear effect
stochastic instead of deterministic generation at epoch 1 (ablation)PGDH · CIFAR-10 (64-bit)MAP: 24.51 -> 10.10Hurt

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