AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells

Gengchen Mai, Krzysztof Janowicz, Bo Yan, Rui Zhu, Ling Cai, Ni Lao

ICLR 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 15 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
Use multi-scale Space2Vec theory encoding rather than RBF encodingPOI location modeling · Yelp Las Vegas testMRR: 0.123 (0.001) -> 0.144 (0.001)Improved
Use multi-scale grid-cell representations rather than Adaptive Kernel priorsFine-grained image classification · BirdSnap†accuracy: 78.65 -> 79.44Improved
Use multi-scale theory encoding rather than Adaptive Kernel priorsFine-grained image classification · NABirds†accuracy: 81.11 -> 81.59Improved
Use theory encoding with λmin=50 rather than λmin=1k (ablation)POI location modeling · Yelp Las Vegas testMRR: 0.121 (0.001) -> 0.144 (0.001)Improved
Use theory encoding with λmin=50 rather than λmin=500 (ablation)POI location modeling · Yelp Las Vegas testMRR: 0.129 (0.001) -> 0.144 (0.001)Improved
Use the full theory encoding rather than block-diagonal constraints (ablation)POI location modeling · Yelp Las Vegas testMRR: 0.094 (0.002) -> 0.144 (0.001)Improved
Use theory encoding rather than hexa encoding (ablation)POI location modeling · Yelp Las Vegas testMRR: 0.105 (0.001) -> 0.144 (0.001)Improved
Use theory encoding with λmin=10 rather than λmin=200 (ablation)POI spatial context modeling · Yelp Las Vegas testMRR: 0.170 (0.001) -> 0.185 (0.002)Improved
Add spatial relationship encoding to context attention (ablation)Space2Vec context decoder · Yelp Las Vegas testMRR: 0.167 (0.006) -> 0.185 (0.002)Improved
Use theory rather than grid encoding (ablation)Fine-grained image classification · BirdSnap† and NABirds†accuracy: 79.44 vs 79.35; 81.28 vs 81.59Mixed

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