AI Paper Atlas

Research map / Image generation / Fast diffusion sampling

Ensemble Diffusion for Retrieval

Song Bai, Zhichao Zhou, Jingdong Wang, Xiang Bai, Longin Jan Latecki, Qi Tian

ICCV 2017 · Image generation › Fast diffusion sampling · approach: Diffusion models as perception tools · 101 citations (OpenAlex)

Read the paper

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 learned sparse weights (RED) instead of equal-weight naive fusion (ablation)diffusion-based fusion · ModelNet40mAP: 84.55 -> 86.30Improved
add learned sparse weights (RED) instead of equal-weight naive fusion (ablation)diffusion-based fusion · ModelNet40AUC: 85.26 -> 87.03Improved
add learned weights (RED) instead of equal-weight naive fusion (ablation)diffusion-based fusion · HolidaysmAP: 90.69 -> 93.32Improved
add learned weights (RED) instead of equal-weight naive fusion (ablation)diffusion-based fusion · UkbenchN-S score: 3.907 -> 3.938Improved
replace the exponential weight learner of SN with RED's sparse-capable weight learning (ablation)similarity fusion · HolidaysmAP: 91.72 -> 93.32Improved
fuse the weak PANORAMA similarity with Vol. CNN using tensor product fusion (ablation)Vol. CNN · ModelNet40mAP: 79.53 -> 67.16Hurt
fuse GIFT with Vol. CNN using tensor product fusion (ablation)Vol. CNN · ModelNet40mAP: 79.53 -> 83.23Improved
use RED instead of the best tensor product fusion pair (ablation)similarity fusion · ModelNet40mAP: 85.12 -> 86.30Improved
fuse 5 random noisy similarities with naive fusion (ablation)naive fusion · HolidaysmAP: 14.82Hurt
fuse 5 random noisy similarities with RED (ablation)RED · HolidaysmAPNo clear effect
vary the weight regularizer lambda in RED (ablation)RED · HolidaysmAPNo clear effect
swap the order of fusion (GIFT with ResNet) in tensor product fusion (ablation)tensor product fusion · ModelNet40mAP: 85.08 vs 85.12Mixed

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