AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

Granularity-Aware Adaptation for Image Retrieval over Multiple Tasks

Jon Almazán, Byungsoo Ko, Geonmo Gu, Diane Larlus, Yannis Kalantidis

ECCV 2022 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 8 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 pseudo-granularity adaptors with attention-consistency fusionDINO ViT-S · FlowersmAP: 57.0 -> 61.9Improved
add pseudo-granularity adaptors with attention-consistency fusionDINO ViT-S · ProductsmAP: 31.5 -> 33.6Improved
pretrain adaptors on pseudo-labels instead of random initialization (ablation)GrAPPa fusion · CUBmAP: 4.5 -> 24.1Improved
pretrain adaptors on pseudo-labels instead of random initialization (ablation)GrAPPa fusion · CarsmAP: 1.7 -> 4.0Improved
use neighbor attention consistency instead of transformation consistency for fusion (ablation)GrAPPa · CUBmAP: 23.5 -> 24.1Improved
use neighbor attention consistency instead of transformation consistency for fusion (ablation)GrAPPa · ProductsmAP: 33.2 -> 33.6Improved
use learned attention fusion instead of average pooling (ablation)GrAPPa · ProductsmAP: 34.4 -> 33.6Hurt
use learned attention fusion instead of average pooling (ablation)GrAPPa · CUBmAP: 23.1 -> 24.1Improved
fuse all eight adaptor sets rather than pick best single set (ablation)GrAPPa-AC · Food-101mAP: 18.4 -> 19.3Improved
use finest pseudo-granularity (P8) instead of P3 only (ablation)single adaptor set · CUBmAP: 24.5 -> 6.6Hurt
use finest pseudo-granularity (P8) instead of P1 (ablation)single adaptor set · ProductsmAP: 29.6 -> 43.7Improved
add a single randomly initialized adaptor (ablation)DINO · CUBmAP: 22.9 -> 7.8Hurt

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