AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Benchmarking and Analyzing Generative Data for Visual Recognition

Bo Li, Haotian Liu, Liangyu Chen, Yong Jae Lee, Chunyuan Li, Ziwei Liu

TPAMI 2025 · Image generation › Autoregressive and latent generation · approach: Synthetic training data from generators · 5 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 defined (dataset-specific) templates instead of simple template (ablation)Stable Diffusion · GenBench 22 datasets meanCLER score (%): 48.83 -> 51.60Improved
use defined templates instead of simple template (ablation)GLIDE · GenBench 22 datasets meanCLER score (%): 48.48 -> 52.04Improved
use category enhancement (T5 sentence expansion) instead of simple template (ablation)Stable Diffusion · GenBench 22 datasets meanCLER score (%): 48.83 -> 47.68Hurt
use category enhancement instead of simple template (ablation)GLIDE · GenBench 22 datasets meanCLER score (%): 48.48 -> 46.93Hurt
add negative prompts on top of defined templates (ablation)Stable Diffusion · GenBench 22 datasets meanCLER score (%): 51.60 -> 51.10No clear effect
add negative prompts and restrictive descriptions on top of defined templates (ablation)Stable Diffusion · GenBench 22 datasets meanCLER score (%): 51.60 -> 52.01No clear effect
add negative prompts and restrictive descriptions (ablation)Stable Diffusion · ImageNet-1K and CIFAR-10 (20-shot)CLER score (%): 61.07 -> 61.45Improved
use Stable Diffusion 2.1 instead of GLIDE with simple promptgenerative data · GenBench 22 datasets meanCLER score (%): 48.48 -> 48.83No clear effect
inject original data (5-shot) via Textual InversionStable Diffusion · GenBench 17 datasets mean (5-shot generated)CLER score (%): 45.92 -> 50.52Improved
inject original data (5-shot) via Textual InversionStable Diffusion · GenBench 17 datasets mean (100-shot generated)CLER score (%): 48.64 -> 53.90Improved
inject retrieval data via Textual InversionStable Diffusion · GenBench 17 datasets mean (5-shot generated)CLER score (%): 45.92 -> 46.46Improved
inject retrieval data via Textual InversionStable Diffusion · GenBench 17 datasets mean (100-shot generated)CLER score (%): 48.64 -> 47.75Hurt

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