AI Paper Atlas

Research map / Architectures and efficiency / CNN design

Deep Scene Image Classification With the MFAFVNet

Yunsheng Li, Mandar Dixit, Nuno Vasconcelos

ICCV 2017 · Architectures and efficiency › CNN design · approach: Filter design and trained-filter analysis · 72 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
initialize PCA and MFA layers from pre-trained statistics instead of randomly (ablation)MFAFVNet (VGG-16, scale 96) · MIT Indooraccuracy (%): 77.3 -> 80.3Improved
initialize PCA and MFA layers from pre-trained statistics instead of randomly (ablation)MFAFVNet (VGG-16, scale 96) · SUNaccuracy (%): 56.2 -> 62.51Improved
initialize PCA and MFA layers from pre-trained statistics instead of randomly (ablation)MFAFVNet (AlexNet, scale 96) · MIT Indooraccuracy (%): 69.82 -> 71.44Improved
initialize PCA and MFA layers from pre-trained statistics instead of randomly (ablation)MFAFVNet (AlexNet, scale 96) · SUNaccuracy (%): 50.23 -> 54.14Improved
increase regularization strength lambda from 0.01 to 1 (ablation)MFAFVNet (VGG-16) · MIT Indooraccuracy (%): 79.79 -> 80.3Improved
increase regularization strength lambda from 0.01 to 1 (ablation)MFAFVNet (AlexNet) · MIT Indooraccuracy (%): 70.69 -> 71.44Improved
increase lambda beyond 1 (10, 100) (ablation)MFAFVNet (VGG-16) · MIT Indooraccuracy (%): 80.3 -> 80.12 (lambda 10), 80.14 (lambda 100)No clear effect
combine three patch scales instead of single scale 96 (ablation)MFAFVNet (VGG-16) · MIT Indooraccuracy (%): 80.3 -> 81.12Improved
combine three patch scales instead of single scale 96 (ablation)MFAFVNet (VGG-19) · MIT Indooraccuracy (%): 80.5 -> 82.66Improved
combine three patch scales instead of single scale 96 (ablation)MFAFVNet (AlexNet) · SUNaccuracy (%): 54.14 -> 57.15Improved
use larger single patch size 160 instead of 96 (ablation)MFAFVNet (VGG-16) · MIT Indooraccuracy (%): 80.3 -> 78.01Hurt
add first-order term (Eq. 19) to second-order MFA-FV layer (ablation)MFAFVNet · scene classificationaccuracy (%)No 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