AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Diverse and Accurate Image Description Using a Variational Auto-Encoder with an Additive Gaussian Encoding Space

Liwei Wang, Alexander Schwing, Svetlana Lazebnik

NeurIPS 2017 · Image generation › Autoregressive and latent generation · approach: Hierarchical VQ-VAE generation · 144 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
Use the additive Gaussian prior instead of the fixed Gaussian priorCVAE captioning · MSCOCO test, oracleCIDEr: 0.910 -> 1.517Improved
Use the additive Gaussian prior instead of the Gaussian mixture priorCVAE captioning · MSCOCO test, oracleCIDEr: 1.430 -> 1.517Improved
Use the additive Gaussian prior instead of the Gaussian mixture priorCVAE captioning · MSCOCO test, diversity% unique per image: 0.594 -> 0.764Improved
Increase z samples from 20 to 100 (ablation)AG-CVAE · MSCOCO test, oracleCIDEr: 1.308 -> 1.517Improved
Increase z samples from 20 to 100 (ablation)AG-CVAE · MSCOCO test, diversity% unique per image: 0.764 -> 0.550Hurt
Add beam search with beam size 2 (ablation)AG-CVAE with 20 z samples · MSCOCO test, oracleCIDEr: 1.259 -> 1.308Improved
Add the object vector (ablation)AG-CVAE with 20 z samples and std 2 · MSCOCO test, oracleCIDEr: 1.230 -> 1.259Improved
Use std 2 rather than std 0.1 (ablation)AG-CVAE without object vector · MSCOCO test, oracleCIDEr: 1.230 -> 1.230No clear effect
Replace the additive Gaussian prior with a Gaussian mixture prior (ablation)CVAE with 100 z samples and object vector · MSCOCO test, oracleCIDEr: 1.517 -> 1.378Hurt
Use 100 rather than 20 z samples (ablation)AG-CVAE · MSCOCO test, diversity% unique per image: 0.764 -> 0.550Hurt

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