AI Paper Atlas

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

NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection

Jiyang Gao, Jiang Wang, Shengyang Dai, Li-Jia Li, Ram Nevatia

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 97 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 distillation head to Det-AZ&RPN-A (ablation)NOTE-RCNN mining · MSCOCO 2017 mined box precisionbox precision (%): 83.7 -> 89.9 (iteration 5)Improved
add distillation head to Det-AZ&RPN-A (ablation)NOTE-RCNN mining · MSCOCO 2017 number of mined boxesnumber of mined boxes: 60899 -> 42756 (iteration 5)Hurt
add distillation to NOTE-RCNN (ablation)NOTE-RCNN · ILSVRC 2013 target categoriesmAP: 42.6 -> 43.7Improved
add seed annotations to FRCN+SemiMILFaster RCNN + SemiMIL · ILSVRC 2013 target categoriesmAP: 36.9 -> 38.7Improved
replace Faster RCNN with NOTE-RCNN (ablation)SemiMIL+Seed · ILSVRC 2013 target categoriesmAP: 38.7 -> 39.9Improved
separate seed and mined annotations with extra heads (vs Naive Faster RCNN) (ablation)Naive Faster RCNN · MSCOCO 2017mAPImproved
zero the background loss in det-cls-a (Det-AZ vs Det-A) (ablation)Det-A · MSCOCO 2017 and ILSVRC 2013mAPImproved
add ensemble classification head to RPN (Det-AZ&RPN-A vs Det-AZ) (ablation)Det-AZ · MSCOCO 2017mAPImproved
add ensemble classification head to RPN (Det-AZ&RPN-A vs Det-AZ) (ablation)Det-AZ · ILSVRC 2013mAPNo clear effect
half-distill: distillation in first 4 iterations then none (ablation)Det-AZ&RPN-A&Distill · MSCOCO 2017mAPMixed
add OpenImage v4 image-level labels with iterative training-mining on full MSCOCO seedDet-AZ&RPN-A · MSCOCO + OpenImage v4mAP@[0.5:0.95]: 32.2 -> 34.0Improved
vary seed annotation amount (12 to 96 images per category) (ablation)Det-AZ&RPN-A · MSCOCO 2017mAPImproved

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