AI Paper Atlas

Research map / Architectures and efficiency / CNN design

When Naive Bayes Nearest Neighbors Meet Convolutional Neural Networks

Ilja Kuzborskij, Fabio Maria Carlucci, Barbara Caputo

CVPR 2016 · Architectures and efficiency › CNN design · approach: Compact CNN architectures · 23 citations (OpenAlex)

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 patches from multiple scales instead of using only one patch scale (ablation)CNN-NBNN · Scene 15, UIUC Sports, and MIT IndooraccuracyImproved
Use larger patches rather than only smaller patches (ablation)CNN-NBNN · Scene recognitionaccuracyImproved
Increase sampling density from sparse to dense (ablation)CNN-NBNN · Scene recognitionaccuracyNo clear effect
Use 16px patches (ablation)CNN-NBNN · Scene recognitionaccuracyMixed
Use CNN features before ReLU rather than after ReLU (ablation)CNN-NBNN · Scene recognitionaccuracyImproved
Replace NBNL with scalable NBNLNBNL · Scene 15, Sports 8, and MIT Indooraccuracy: 91.5 -> 91.638; 94.29 -> 95.268; 72.592 -> 72.786No clear effect
Replace NBNL with scalable NBNLNBNL · Scene 15, Sports 8, and MIT Indoortraining time: 5729.2 -> 210.3; 1024.4 -> 63.564; 9690 -> 304.26Improved
Use CNN-sNBNL rather than a linear SVM on Hybrid CNN featuresSUN-397 scene recognition · SUN-397accuracy: 53.86 ± 0.21% -> 55.8 ± 0.29%Improved
Use CNN-sNBNL rather than a linear SVM on Places-205 CNN featuresSUN-397 scene recognition · SUN-397accuracy: 54.32 ± 0.14% -> 55.8 ± 0.29%Improved
Use CNN-sNBNL rather than CNN-NBNLCNN-NBNL · UIUC Sportsaccuracy: 95.29 ± 0.61 -> 95.28 ± 0.68No clear effect
Use CNN-sNBNL rather than CNN-NBNLCNN-NBNL · MIT Indooraccuracy: 73 ± 0.36 -> 72.79 ± 0.73No clear effect

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