AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

Semi-Supervised Generative Adversarial Hashing for Image Retrieval

Guan'an Wang, Qinghao Hu, Jian Cheng, Zengguang Hou

ECCV 2018 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 40 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 adversary ranking loss (with generative model) to supervised-only baseline (ablation)deep hashing model · CIFAR-10mAP: improves the baseline by 3.2% ~4.0%Improved
add adversary ranking loss (with generative model) to supervised-only baseline (ablation)deep hashing model · NUS-WIDEmAP: improves the baseline by 0.9% ~2.8%Improved
add semi-supervised ranking loss to supervised-only baseline (ablation)deep hashing model · CIFAR-10mAP: improves the baseline by 4.8% ~5.7%Improved
add semi-supervised ranking loss to supervised-only baseline (ablation)deep hashing model · NUS-WIDEmAP: improves the baseline by 3.2% ~5.1%Improved
add adversary ranking loss on top of semi-supervised ranking loss (w/ ssr -> SSGAH) (ablation)SSGAH · CIFAR-10 (48bits)mAP: 0.846 -> 0.855Improved
add semi-supervised ranking loss on top of adversary ranking loss (w/ ar -> SSGAH) (ablation)SSGAH · NUS-WIDE (48bits)mAP: 0.812 -> 0.865Improved
add adversary ranking loss on top of semi-supervised ranking loss (ablation)SSGAH · NUS-WIDE (12bits)mAP: 0.810 -> 0.835Improved
use semi-supervised generative adversarial hashing instead of supervised-only baseline with less supervisiondeep hashing model · CIFAR-10 and NUS-WIDE (48bits)mAPImproved
use unlabeled data via semi-supervised deep hashing instead of supervised deep hashing (NINH, CNNH)deep hashing · CIFAR-10 and NUS-WIDEmAPImproved
use CNN fc7 features instead of hand-crafted features for traditional hashingSDH · CIFAR-10 (48bits)mAP: 0.360 -> 0.542Improved
use CNN fc7 features instead of hand-crafted features for traditional hashingITQ · NUS-WIDE (48bits)mAP: 0.477 -> 0.661Improved
use SSGAH instead of SSDH for retrieval of unseen classeshashing · NUS-WIDE unseen classes (48bits)mAP: 0.551 -> 0.579Improved

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