atlas

Research map / Image generation / GANs

Interactive Dual Generative Adversarial Networks for Image Captioning

AAAI 2020 · Image generation › GANs · approach: Large-scale GAN latent analysis · 29 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 retrieval-based generator Gθ2 (ablation)IDGAN · MSCOCO Karpathy testCIDEr: 121.7 -> 123.5Helped
add retrieval-based discriminator Dφ2 (ablation)IDGAN · MSCOCO Karpathy testCIDEr: 121.3 -> 123.5Helped
add generation discriminator Dφ1 (ablation)IDGAN · MSCOCO Karpathy testCIDEr: 122.1 -> 123.5Helped
add copy mechanism from retrieved guidance captions (ablation)IDGAN · MSCOCO Karpathy testCIDEr: 122.7 -> 123.5Helped
add retrieval-based discriminator Dφ2 (ablation)IDGAN · MSCOCO Karpathy testBLEU-4: 36.9 -> 38.5Helped
add retrieval-based generator Gθ2 (ablation)IDGAN · MSCOCO Karpathy testBLEU-4: 36.8 -> 38.5Helped
add copy mechanism (ablation)IDGAN · MSCOCO Karpathy testBLEU-4: 38.2 -> 38.5Helped
IDGAN dual adversarial retrieval-generation vs TopDown backboneTopDown · MSCOCO Karpathy testCIDEr: 120.1 -> 123.5Helped
IDGAN vs TopDown human evaluationTopDown · MSCOCO human evalInformativeness: 3.25 -> 3.32Helped

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