AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Free-Lunch Augmentation by Revisiting Diffusion-Based Data Generation for Cross-Domain Few-Shot Object Detection

Zijian Zhuang, Yixiong Zou, Yuhua Li, Ruixuan Li

ECCV 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Domain-adaptive object detection · 0 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 SITN synthesis to CD-ViTOCD-ViTO (ViT-L) · CDFSOD 1-shot averagemAP: 13.9 -> 17.0Improved
add SITN to GroundDINOGroundDINO (Swin-B) · CDFSOD 1-shot averagemAP: 24.0 -> 34.3Improved
add SITN to ViTDeT-FT on ArTaxOr and DIORViTDeT-FT · CDFSOD 1-shot ArTaxOrmAP: 5.9 -> 5.4 (ArTaxOr); average 5.4 -> 6.5Mixed
add SITN to ETSETS (Swin-B) · CDFSOD 1-shot averagemAP: 21.9 -> 32.1Improved
add background inpainting only (ablation)CD-ViTO · ArTaxOr 1-shotmAP: 21.0 -> 24.9Improved
combine foreground and background without selection (ablation)CD-ViTO · Deepfish 1-shotmAP: 20.3 -> 13.5Hurt
add selection module (ablation)SITN · UODD 1-shotmAP: 2.1 -> 5.6Improved
use foreground-only inpainting (ablation)CD-ViTO · Deepfish 1-shotmAP: 20.3 -> 18.3Hurt
use standard diffusion generators (Diffmix, IP-Adapter, etc.) instead of SITN (ablation)CD-ViTO · CDFSOD 1-shot averagemAP: 13.9 (baseline) -> 4.8 (Diffmix)Hurt
apply Mixup augmentation (ablation)CD-ViTO · CDFSOD 1-shot averagemAP: 13.9 -> 8.7Hurt
use Nucleus-Image generator inside SITN (ablation)SITN · CDFSOD averagemAP: 34.3 -> 32.1No clear effect
apply SITN to FPTrans for segmentationFPTrans · CDFSS averagemIoU: 62.2 -> 66.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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