AI Paper Atlas

Research map / Detection and segmentation / CNN features

A Large Contextual Dataset for Classification, Detection and Counting of Cars with Deep Learning

T. Nathan Mundhenk, Goran Konjevod, Wesam A. Sakla, Kofi Boakye

ECCV 2016 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 396 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 residual projection shortcut to Inception layers (ResCeption)GoogLeNet/Inception · COWC patch classificationpatch accuracy: 99.12% -> 99.14%Improved
use Inception/ResCeption instead of AlexNetclassification network · COWC patch classificationpatch accuracy: 97.62% -> 99.14%Improved
train on non-Utah data and test on UtahResCeption · COWC patch classificationpatch accuracy: 99.14% -> 98.89%Mixed
increase visible context margin up to 192x192 pixels (ablation)GoogLeNet · COWC patch classificationpatch accuracyImproved
add residual shortcut (ResCeption) over Inceptioncounting network · COWC patch countingMAE: 0.257 -> 0.255Improved
double the depth of ResCeption with one error output (Taller o1)ResCeption · COWC patch countingexactly correct count: 80.34% -> 81.07%Improved
use Inception/ResCeption instead of AlexNetcounting network · COWC patch countingexactly correct count: 67.97% -> 80.35%Improved
add three error outputs to the taller ResCeption (ablation)ResCeption Taller · COWC scene countingtotal error: 1.19% -> 0.46%Improved
average counts over four offset stridesResCeption Taller o3 · COWC scene countingMAE: 6.14% -> 5.15%Improved
average counts over four offset stridesResCeption Taller o3 · COWC scene countingtotal error: 0.46% -> 0.20%Improved
use AlexNet instead of larger networks for speedAlexNet · COWC scene countingtime per 2048x2048 scene (s): 0.087 vs 0.773Mixed
raise softmax output to the power of 16ResCeption heat map · COWC detectionheat map gradientNo 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