AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Diffusion-Based Data Augmentation for Image Recognition: A Systematic Analysis and Evaluation

Zekun Li, Yinghuan Shi, Yang Gao, Dong Xu

IJCV 2026 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 1 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 Full Concatenation instead of Full Replacement for synthetic samples (ablation)GIF · Caltech-101 (from scratch)top-1 accuracy: 51.43 -> 76.11Improved
use Full Concatenation instead of Full Replacement (ablation)GIF · CIFAR-100 (from scratch)top-1 accuracy: 31.78 -> 68.23Improved
use Local Random Replacement instead of Full Concatenation with pretrained classifier (ablation)Diff-II · Birds 10-shot (pretrained)top-1 accuracy: 71.07 -> 72.96Improved
use Full Replacement instead of Local Random Replacement (ablation)Diff-II · Birds 5-shot (pretrained)top-1 accuracy: 61.29 -> 41.07Hurt
use Full Replacement instead of Full Concatenation (structure-preserving generation) (ablation)DiffuseMix · Birds 5-shot (pretrained)top-1 accuracy: 53.72 -> 55.88Improved
use Global instead of Local Random Replacement (ablation)Diff-II · Birds 10-shot (pretrained)top-1 accuracy: 72.96 -> 72.47No clear effect
raise SDEdit transition strength from 0.1 to 0.9 (ablation)Real Guidance · Caltech-101 (from scratch)top-1 accuracy: 54.96 -> 65.38Improved
raise SDEdit transition strength from 0.1 to 0.9 (ablation)Real Guidance · ImageNet-100 (from scratch)top-1 accuracy: 66.30 -> 77.12Improved
add DreamBooth-LoRA UNet fine-tuning on top of Textual Inversion (ablation)DA-Fusion (vs Diff-Aug) · Aircraft few-shot averagetop-1 accuracy: 32.53 -> 34.36Improved
add inter-class image mixup in generation (ablation)Diff-Aug · Birds few-shot averagetop-1 accuracy: 50.11 -> 53.67Improved
fine-tune diffusion model (Diff-Mix) instead of untuned low-strength generation on medical dataReal Guidance · Blood 25/class (from scratch)top-1 accuracy: 86.67 -> 70.44Hurt
apply DiffDA at fine species granularityDiff-Mix · Semi-iNat species leveltop-1 accuracy: 41.88 -> 37.04Hurt

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