AI Paper Atlas

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

Do Deep Neural Networks Suffer from Crowding?

Anna Volokitin, Gemma Roig, Tomaso A Poggio

NeurIPS 2017 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 11 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 flankers to isolated-target test imagesDCNNs and eccentricity-dependent models trained on isolated targets · MNIST target recognition with flankersaccuracyHurt
Increase the number of flankersDCNNs and eccentricity-dependent models trained on isolated targets · MNIST target recognition with flankersaccuracyHurt
Increase target–flanker spacingDCNNs trained on isolated targets · MNIST targets at fixed eccentricityaccuracyImproved
Train with flankers in the same configuration used at test timeDCNN and eccentricity-dependent models · MNIST target recognition with flankersaccuracyImproved
Train with clutter, then test with different clutter configurationsDCNN and eccentricity-dependent models · MNIST target recognition with unseen flanker configurationsaccuracyHurt
Use more target-similar flankersDCNNs trained on isolated targets · MNIST targets with MNIST, Omniglot, or notMNIST flankersaccuracyHurt
Use notMNIST rather than odd MNIST or Omniglot flankersDCNNs trained on isolated targets · MNIST target recognition with different flanker datasetsaccuracyHurt
Use Omniglot rather than odd MNIST flankersDCNNs trained on isolated targets · MNIST target recognition with different flanker datasetsaccuracyImproved
Add spatial pooling rather than using no total pooling (ablation)DCNNs · MNIST targets without flankersaccuracyImproved
Add contrast normalization across scales (ablation)Eccentricity-dependent model · MNIST target recognition across eccentricitiesaccuracyImproved
Pool across scales at the beginning rather than at the end (ablation)Eccentricity-dependent model · MNIST target recognition with flankersaccuracyHurt
Use the eccentricity-dependent model rather than a DCNNModels trained on isolated targets · MNIST targets embedded in Places imagesaccuracyMixed

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