AI Paper Atlas

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

On Numerosity of Deep Neural Networks

Xi Zhang, Xiaolin Wu

NeurIPS 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 2 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
Increase the ANOVA test sample size from the original small sampleObject recognition DCNN · Dot displaysnumerosity-selective neurons: 9.6% -> about 2% (20 images per combination); zero (80 images per combination)Hurt
Use the original small ANOVA sample on randomly initialized weightsUntrained DCNN · Dot displaysnumerosity-selective neurons: 12.8% (untrained) vs 9.6% (object recognition network)Mixed
Train the DCNN specifically for numerosity classificationNu-Net · Numerosity test, same distributionaccuracy: 95.6%Improved
Train the DCNN specifically for numerosity classificationNu-Net · Numerosity test, same distributionnumerosity-selective neurons: 68.4%Improved
Increase object-size variation in test images by 50% relative to trainingNu-Net · Numerosity testaccuracy: 95.6% -> 64.2%Hurt
Test with object sizes outside the training rangeNu-Net · Numerosity test, distribution shiftaccuracyMixed
Train the Nu-Net with supervised numerosity labelsNu-Net · Distribution-shifted numerosity, numbers 1 to 4accuracyImproved

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