AI Paper Atlas

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

Robots Understanding Contextual Information in Human-Centered Environments Using Weakly Supervised Mask Data Distillation

Daniel Dworakowski, Angus Fung, Goldie Nejat

IJCV 2022 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 6 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
increase binary search steps from 1 to 6 (2 models, 32 samples) (ablation)WeSuperMaDD · ICDAR-13 trainF1: +40%Improved
increase binary search steps from 1 to 6 (1 model, 1 sample) (ablation)WeSuperMaDD · ICDAR-13 trainF1: +210%Improved
add second text recognition model (TPS) to ensemble or raise samples to 32 (one search step) (ablation)WeSuperMaDD · ICDAR-13 trainF1: +12 to 20 F1Improved
increase search steps beyond 4 with 32 samples and 2 models (ablation)WeSuperMaDD · ICDAR-13 trainF1: plateau at approximately 81 at 4 stepsNo clear effect
WeSuperMaDD pseudo labels instead of GrabCutPSL generation · ICDAR-13 testF1: 57.25 -> 80.69Improved
WeSuperMaDD pseudo labels instead of PyramidPSL generation · ICDAR-13 testF1: 43.12 -> 80.69Improved
WeSuperMaDD pseudo labels instead of Naive full-box labelsPSL generation · ICDAR-13 testF1: 67.44 -> 80.69Improved
weakly supervised WeSuperMaDD instead of semi-supervised SGPPSL generation · ICDAR-13 test (size-weighted)F1: 78.87 -> 79.00No clear effect
train detector with WeSuperMaDD PSLs instead of Naive PSLs (detection)RetinaNet-style text CNN · ICDAR-13/15/17 and grocerydetection F1: between 0.12 and 1.50 higherImproved
train detector with WeSuperMaDD PSLs instead of Naive PSLs (segmentation)RetinaNet-style text CNN · ICDAR-13/15/17 and grocerysegmentation F1 after PRP: 41.76 to 71.03 -> 67.10 to 85.24, gain of 42% to 83%Improved
WCNN versus other one-stage detectorsWCNN · ICDAR-13 and ICDAR-15detection F1: +0.56 and +3.25Improved
WCNN versus STELA one-stage detectorWCNN · ICDAR-17detection F1: 2.85 lowerHurt

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