AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

RelNN: A Deep Neural Model for Relational Learning

Seyed Mehran Kazemi, David Poole

AAAI 2018 · Detection and segmentation › Open-set and few-shot detection · approach: Visual relationship and scene graph detection · 46 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 RelNN instead of Matrix FactorizationMovieLens Gender prediction · MovieLens Genderaccuracy: 0.7550 ± 0.0073 -> 0.7902 ± 0.0051Improved
Use RelNN instead of Matrix FactorizationMovieLens Gender prediction · MovieLens Genderlog loss: 0.7318 ± 0.0073 -> 0.6548 ± 0.0026Improved
Use RelNN instead of Matrix FactorizationMovieLens Gender prediction · MovieLens GenderMSE: 0.1649 ± 0.0026 -> 0.1459 ± 0.0009Improved
Use RelNN instead of Collaborative FilteringPAKDD Gender prediction · PAKDD Genderaccuracy: 0.8806 -> 0.8853 ± 0.0002Improved
Use RelNN instead of Collaborative FilteringPAKDD Gender prediction · PAKDD Genderlog loss: 0.5135 -> 0.5093 ± 0.0037Improved
Use RelNN instead of Collaborative FilteringPAKDD Gender prediction · PAKDD GenderMSE: 0.1026 -> 0.1009 ± 0.0008Improved
Use RelNN instead of Collaborative FilteringYelp Business Prediction · Yelp Business Predictionaccuracy: 0.6712 -> 0.6927 ± 0.0077Improved
Use RelNN instead of Collaborative FilteringYelp Business Prediction · Yelp Business Predictionlog loss: 0.8757 -> 0.8531 ± 0.0090Improved
Use RelNN instead of Collaborative FilteringYelp Business Prediction · Yelp Business PredictionMSE: 0.2084 -> 0.2023 ± 0.0024Improved
Use RelNN instead of Collaborative FilteringMovieLens Age prediction · MovieLens AgeMSE: 90.8742 -> 62.7000 ± 0.7812Improved
Add hidden layers (ablation)RelNN on MovieLens · MovieLens gender and age predictionlog lossImproved
Add hidden layers (ablation)RelNN on MovieLens · MovieLens gender and age predictionMSEImproved

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