AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Efficient Diffusion on Region Manifolds: Recovering Small Objects With Compact CNN Representations

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondrej Chum

CVPR 2017 · Image generation › Autoregressive and latent generation · approach: Retrieval and matching with generative features · 191 citations (OpenAlex)

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 diffusion over region descriptors instead of global image descriptorsCNN image retrieval · INSTREmAP: 47.7 -> 80.0Improved
use diffusion over region descriptors instead of global image descriptorsCNN image retrieval · Oxford5kmAP: 77.7 -> 93.2Improved
use diffusion over region descriptors instead of global image descriptorsCNN image retrieval · Oxford105kmAP: 70.1 -> 90.3Improved
use diffusion over region descriptors instead of global image descriptorsCNN image retrieval · Paris6kmAP: 84.1 -> 96.5Improved
use diffusion over region descriptors instead of global image descriptorsCNN image retrieval · Paris106kmAP: 76.8 -> 92.6Improved
use generalized max pooling instead of sum pooling after regional diffusion (ablation)Regional diffusion · INSTRE; Oxford5k; Oxford105k; Paris6k; Paris106kmAP: 79.1 -> 80.0; 92.2 -> 93.2; 90.6 -> 91.6; 96.1 -> 96.5; 94.4 -> 94.6Improved
handle unseen queries by weighting their nearest neighbors without modifying the affinity matrix (ablation)Regional diffusion · INSTREmAP: 77.7 -> 80.0Improved
reduce each image's regional descriptors with per-image GMMs (ablation)Regional diffusion · Oxford5kmAP: 93.2 -> 91.5Hurt
reduce each image's regional descriptors with per-image GMMs (ablation)Regional diffusion · Oxford105kmAP: 90.3 -> 84.7Hurt
reduce each image's regional descriptors with per-image GMMs (ablation)Regional diffusion · INSTREmAP: 80.0 -> 77.5Hurt
replace exhaustive affinity-graph construction with Dong et al.'s approximate k-NN graph (ablation)Regional diffusion · Oxford105kmAP: 92.5 -> 91.6Hurt
replace exhaustive affinity-graph construction with Dong et al.'s approximate k-NN graph (ablation)Regional diffusion · Paris106kmAP: 95.2 -> 94.6Hurt

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