AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

ALWOD: Active Learning for Weakly-Supervised Object Detection

Yuting Wang, Velibor Ilic, Jiatong Li, Branislav Kisačanin, Vladimir Pavlovic

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 31 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 auxiliary generated fully-labeled set S^X to the initial student-teacher training (ablation)ALWOD (VGG16) · RealPizza10 initial detectorAP50: 11.9 -> 18.8Improved
add auxiliary generated fully-labeled set S^X to the initial student-teacher training (ablation)ALWOD (VGG16) · VOC2007 initial detectorAP50: 55.4 -> 60.1Improved
add auxiliary set S^X when fine-tuning the MIST base detector in BiB (ablation)BiB (VGG16, MIST) · VOC2007 and RealPizza10 initial detectorAP50: 54.5 -> 50.6 (VOC2007); 15.2 -> 14.0 (RealPizza10)Hurt
use product of model disagreement and image uncertainty instead of sum (ablation)ALWOD acquisition function · VOC2007, COCO2014, RealPizza10AP50Improved
use ALWOD acquisition function instead of uniform sampling (ablation)ALWOD (ResNet50) · VOC2007, COCO2014, RealPizza10AP50Improved
use core-set or loss-prediction acquisition instead of uniform sampling (ablation)ALWOD framework · VOC2007, COCO2014, RealPizza10AP50Hurt
use entropy-sum acquisition instead of the proposed functions (ablation)ALWOD framework · RealPizza10, COCO2014AP50Hurt
use selecting-the-box annotation instead of drawing the box (ablation)ALWOD (ResNet50) · RealPizza10AP50: 39.9 -> 39.3No clear effect
use selecting-the-box annotation instead of drawing the boxALWOD (ResNet50) · annotation time per imageannotation time: reduction of over 70%, about 2 secondsImproved
replace Faster-RCNN with Sparse DETR as student and teacher detector (ablation)ALWOD · VOC2007, COCO2014, RealPizza10AP50: 69.1 -> 70.5 (VOC2007, ResNet50)No clear effect
use ALWOD with 5% fully annotated data instead of SSDGMM with 80% fully annotated dataRealPizza10 VGG16 · RealPizza10AP50: 23.4 -> 37.9Improved
use a stronger backbone (VGG16 to Swin-T) in ALWOD (ablation)ALWOD Sparse DETR · VOC2007AP50: 68.0 -> 71.7Improved

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