AI Paper Atlas

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

Active Learning Strategies for Weakly-Supervised Object Detection

Huy V. Vo, Oriane Siméoni, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Jean Ponce

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 25 citations (OpenAlex)

Read the paper

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
replace uniform random selection with BiB selectionMIST + few full annotations · VOC07 (250 images)AP50: 61.1 -> 63.5Improved
add difficulty-aware proposal sampling (DifS) to random selection (ablation)u-random · VOC07 (250 images)AP50: 60.5 -> 61.1Improved
add k-means++ selection on image-level features (ablation)DifS + random · VOC07 (250 images)AP50: 61.1 -> 60.3Hurt
add k-means++ selection on region-level features (ablation)DifS + random · VOC07 (250 images)AP50: 61.1 -> 63.4Improved
use BiB pairs instead of generic region features for diverse selection (ablation)DifS + K selection · VOC07 (250 images)AP50: 63.4 -> 63.5Improved
add DifS to BiB (ablation)BiB · VOC07 (250 images)AP50: 62.6 -> 63.5Improved
add DifS to BiB (ablation)BiB · COCO (800 images)AP50: 34.2 -> 34.1No clear effect
add diversity sampling to BiB-pair image selection (ablation)BiB · VOC07 (cycle 5)AP50: 61.8 -> 63.5Improved
use BiB selection instead of loss-based selectionMIST + few full annotations · COCO (800 images)AP50: 30.4 -> 34.1Improved
use entropy-sum selection instead of uniform randomMIST + few full annotations · COCO (800 images)AP50: 33.0 -> 27.8Hurt
balance classes in random selectionu-random · VOC07 (250 images)AP50: 61.1 -> 61.2No clear effect
vary area ratio mu from 2 to 4 (ablation)BiB · VOC07 (250 images)AP50: 63.1 -> 63.5 -> 63.3No 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