AI Paper Atlas

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

Dynamic Curriculum Learning for Great Ape Detection in the Wild

Xinyu Yang, Tilo Burghardt, Majid Mirmehdi

IJCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 24 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 linear-increase unlabelled sample policy instead of constant use of all unlabelled data (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 60.46 -> 61.62Improved
add warm-up and cool-down phases to linear increase sample policy (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 61.62 -> 64.73Improved
use linear decrease of unlabelled samples instead of increase (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 64.73 -> 53.47Hurt
use dynamic linear 0.1->1 loss weight instead of constant 0.5 (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 63.98 -> 64.73Improved
use constant loss weight 2.0 instead of 0.5 (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 63.98 -> 54.68Hurt
add arctan increasing confidence threshold 0.1->0.6 instead of constant 0.6 (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 62.62 -> 64.73Improved
use very low constant threshold 0.05 instead of 0.6 (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 62.62 -> 51.73Hurt
add weak and strong augmentation policy (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 55.41 -> 64.73Improved
add dynamic cosine teacher momentum 0.998->0.9998 instead of constant 0.999 (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 60.07 -> 64.73Improved
use SWAV self-supervised init instead of random init (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 0.17 -> 64.73Improved
use SWAV self-supervised init instead of supervised ImageNet init (ablation)Dynamic curriculum detector · Extended PanAfrican (PLD 50% labelled, fold1, ablation)mAP: 61.55 -> 64.73Improved
apply full method vs UbTeacher at 10% labelledDynamic curriculum detector · Extended PanAfrican (PLD 10% labelled)mAP: 44.03 -> 45.96Improved

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