AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

AlignDiff: Aligning Diffusion Models for General Few-Shot Segmentation

Ri-Zhao Qiu, Yu-Xiong Wang, Kris Hauser

ECCV 2024 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 6 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 naive text-conditioned GD synthetic samples to the support setHSNet on FSS-1000 · FSS-1000 1-shotoverall IoU: 86.5 -> 81.4Hurt
add semi-supervised mask generation to text-conditioned synthesis (ablation)HSNet + text-conditioned samples · FSS-1000 1-shotoverall IoU: 81.4 -> 87.2Improved
add normalized masked textual inversion on top of semi-supervised masks (ablation)HSNet + AlignDiff · FSS-1000 1-shot (OOD classes)OOD IoU: 86.9 -> 88.2Improved
add normalized masked textual inversion on top of semi-supervised masks (ablation)VAT + AlignDiff · FSS-1000 1-shot (OOD classes)OOD IoU: 88.6 -> 90.6Improved
add text-only samples with semi-supervised masks (no inversion) (ablation)VAT · FSS-1000 1-shotoverall IoU: 90.0 -> 89.8No clear effect
add AlignDiff synthetic samples to SCCANSCCAN · Pascal-5i 1-shotmean IoU: 67.7 -> 69.0Improved
add AlignDiff synthetic samples to SCCANSCCAN · COCO-20i 5-shotmean IoU: 55.1 -> 55.4Improved
add AlignDiff synthetic samples to GAPSGAPS · Pascal-5i GFSS 1-shotnovel IoU: 23.6 -> 43.3Improved
replace GD samples with AlignDiff samplesGAPS · Pascal-5i GFSS 1-shotnovel IoU: 41.2 -> 43.3Improved
add AlignDiff samples to GAPS 5-shotGAPS · COCO-20i GFSS 5-shotbase IoU: 49.1 -> 47.9Mixed
add AlignDiff samples to simple fine-tuningFineTune · Pascal-5i GFSS 1-shotnovel IoU: 3.9 -> 44.9Improved
combine FSS-model masks with attention-map consensus (AlignDiff) instead of attention maps alone (ablation)mask generation · Pascal-5^2 reference-labeled, all imagesmask IoU: 78.6 -> 92.9Improved

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