AI Paper Atlas

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

End-to-End Weakly Supervised Object Detection with Sparse Proposal Evolution

Mingxiang Liao, Fang Wan, Yuan Yao, Zhenjun Han, Jialing Zou, Yuze Wang, Bailan Feng, Peng Yuan, Qixiang Ye

ECCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 28 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 one SPR branch to seed proposals (ablation)SPG · VOC 2007 testmAP: 29.7 -> 42.6Improved
add one SPR branch (ablation)SPG · VOC 2007 testCorLoc: 57.8 -> 61.3Improved
add second and third SPR branches (ablation)SPE · VOC 2007 testmAP: 42.6 -> 42.9No clear effect
add seed proposal box jitter augmentation (delta_aug 0.1) (ablation)SPE · VOC 2007 testmAP: 42.6 -> 45.6Improved
add box jitter augmentation (delta_aug 0.1) (ablation)SPE · VOC 2007 testCorLoc: 61.3 -> 64.0Improved
increase jitter delta_aug from 0.1 to 0.2 (ablation)SPE · VOC 2007 testmAP: 45.6 -> 43.4Hurt
raise delta_seed from 0.2 to 0.4 (ablation)SPG · VOC 2007 testmAP: 29.7 -> 8.9Hurt
lower delta_multi from 1 to 0.5 (ablation)SPE · VOC 2007 testmAP: 37.8 -> 42.6Improved
share all 36 backbone blocks between SPG and SPR instead of 24 (ablation)SPE · VOC 2007 testmAP: 45.6 -> 32.8Hurt
share 12 blocks instead of 24 (ablation)SPE · VOC 2007 testmAP: 45.6 -> 43.1Hurt
use CaiT backbone with Conditional DETR instead of Faster R-CNN (fully supervised)detector · VOC 2007 testmAP: 81.4 -> 77.5Hurt
increase image scale from 384 to 512SPE · COCO 2017AP50: 16.3 -> 18.2Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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