AI Paper Atlas

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

An Extensible Multi-modal Multi-task Object Dataset with Materials

Trevor Scott Standley, Ruohan Gao, Dawn Chen, Jiajun Wu, Silvio Savarese

ICLR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 0 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
Train on data with missing attributes filled using generation-1 predictionsSingle Image models · EMMa test setF1 (Materials): 60.9 -> 72.7Improved
Train on data with missing attributes filled using generation-1 predictionsText models · EMMa test setMnRE (Price): 0.710 -> 0.704Hurt
Train on data with missing attributes filled using generation-1 predictionsEverything models · EMMa test setF1 (Materials): 80.0 -> 86.0Improved
Use images, text, and other available attributes instead of images aloneEverything model · EMMa test setMnRE (Mass): 0.649 -> 0.788Improved
Use images, text, and other available attributes instead of text aloneEverything model · EMMa test setAccuracy (Category): 91.9 -> 92.2Improved
Use the proposed image model rather than Image2MassMass prediction · Image2Mass Amazon test setMnRE (Mass): 0.672 -> 0.709Improved

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