AI Paper Atlas

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

Many-shot from Low-shot: Learning to Annotate using Mixed Supervision for Object Detection

Carlo Biffi, Steven McDonagh, Philip Torr, Aleš Leonardis, Sarah Parisot

ECCV 2020 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised detection · 14 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 shared encoder between branches (ablation)OAM detector · VOC07 (10 shots)mAP (%): 42.1 -> 52.1Improved
add OAM-generated semi-strong images to second branch training (ablation)OAM detector · VOC07 (10 shots)mAP (%): 52.1 -> 58.8Improved
add online bounding box augmentation (ablation)OAM detector with shared encoder and OAM · VOC07 (10 shots)mAP (%): 58.8 -> 59.7Improved
add bounding box augmentation to first branch (with SE and OAM) (ablation)OAM first branch · VOC07 (10 shots)mAP (%): 55.7 -> 59.2Improved
add shared encoder (first branch with BBA) (ablation)OAM first branch · VOC07 (10 shots)mAP (%): 50.2 -> 51.7Improved
use semi-strong images for bounding box regression (ablation)OAM second branch · VOC07mAP (%)Hurt
replace precomputed proposals with learned RPNOAM · VOC07 (10 shots)mAP (%): 59.7 -> 54.6Hurt
add OAM mixed supervision vs Fast R-CNNFast R-CNN · COCO14 (10 shots)AP@.50: 22.1 -> 31.2Improved
add OAM vs BCNetBCNet · VOC07 (10 shots)mAP (%): 57.1 -> 59.7Improved
add OAM mixed supervision vs Fast R-CNN at 10% COCO17Fast R-CNN · COCO17 (10% data)AP@.50: 53.7 -> 54.2No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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