AI Paper Atlas

Research map / Detection and segmentation / CNN features

Active Learning for Deep Detection Neural Networks

Hamed H. Aghdam, Abel Gonzalez-Garcia, Joost van de Weijer, Antonio M. Lopez

ICCV 2019 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 151 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
select frames with the proposed local-divergence score instead of random (guided random)Active learning detector · Caltech Pedestrianmiss rate at FPPI=1Improved
select frames with the proposed score instead of random at the first cycleActive learning detector · Caltech Pedestrian (cycle 1)miss rateNo clear effect
replace local-divergence score with binary entropy (ablation)Proposed pixel score · Caltech Pedestrianmiss rate at FPPI=1Hurt
use local-divergence score instead of MC-Dropout (ablation)MC-Dropout score · Caltech Pedestrianmiss rate at FPPI=1Improved
use local-divergence score instead of binary entropy for pedestrian instance coverage (ablation)Binary entropy score · Caltech Pedestrian (7K frames)pedestrian instances selected: 5243 -> 5706Mixed
increase budget per cycle from 500 to 1500 (ablation)Active learning detector · Caltech Pedestrianmiss rate at FPPI=1Hurt
add max-pooling aggregation instead of averaging pixel scores (ablation)Active learning detector · Caltech Pedestrianmiss rate at FPPI=1Improved
add temporal selection rules (ablation)Active learning detector · Caltech Pedestrianmiss rate at FPPI=1Improved
add temporal smoothing of image scores (ablation)Active learning detector · Caltech Pedestrianmiss rate at FPPI=1No clear effect
use active learning instead of random selection on still imagesActive learning detector · BDD100Kmiss rate at FPPI=1Mixed
increase budget per cycle from 50 to 500 imagesActive learning cycle · Caltech Pedestrian (B=7500)time-to-completion (hours): 1800 -> 190Improved

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