AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Learning Bag-Of-Features Pooling for Deep Convolutional Neural Networks

Nikolaos Passalis, Anastasios Tefas

ICCV 2017 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 79 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 with images of several sizes (Train C) instead of only 28x28 (ablation)CBoF (0, 32) · MNIST testerror (%) at 28x28: 0.88 -> 0.68Improved
train with images of several sizes (Train C) instead of only 28x28 (ablation)CBoF (0, 32) · MNIST test 20x20error (%): 19.69 -> 1.44Improved
train with images of several sizes (Train C) instead of only 28x28 (ablation)CBoF (0, 32) · MNIST test 36x36error (%): 25.39 -> 1.60Improved
train with images of several sizes (Train C) instead of only 227x227 (ablation)CBoF (0, 256) · 15-sceneaccuracy (%): 90.66 -> 92.38Improved
add spatial segmentation level 1 with 128 codewords vs level 0 (ablation)CBoF · MNIST testerror (%): 0.74 -> 0.61Improved
add more RBF neurons (up to 128) without spatial segmentation (ablation)CBoF · MNIST testerror (%): 1.13 -> 0.74Improved
add spatial segmentation (ablation)CBoF · 15-sceneaccuracyNo clear effect
add spatial segmentation (CBoF (1, 32) vs CBoF (0, 128), same parameters) (ablation)CBoF · AFLW yaw (64x64)angular error (deg): 16.23 -> 11.92Improved
use CBoF(1, 32) instead of SPPSPP · MNIST test 20x20error (%): 1.78 -> 0.94Improved
use CBoF (0, 256) instead of CNNCNN · 15-scene (227)accuracy (%): 88.79 -> 91.38Improved
use CBoF(1, 32) instead of CNNCNN · MNIST test (28)error (%): 0.56 -> 0.55No clear effect
add a 1x1 convolutional layer with 64 filters to GMP (ablation)GMP · MNIST test 20x20error (%): 3.22 -> 3.52Hurt

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