AI Paper Atlas

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

Semi-Supervised Pedestrian Instance Synthesis and Detection With Mutual Reinforcement

Si Wu, Sihao Lin, Wenhao Wu, Mohamed Azzam, Hau-San Wong

ICCV 2019 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 10 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 class-specific discriminator Dspe (ablation)Our Model w/o Dspe · Caltech1X (synthesis quality)FID: 103.60 -> 44.18Improved
add class-specific discriminator Dspe (ablation)Our Model w/o Dspe · Caltech1X (synthesis quality)Inception score: 2.39 -> 2.74Improved
add class-conditional discriminator pair (Dcon+Dspe) instead of SN-GAN (ablation)SN-GAN · Caltech1X (synthesis quality)FID: 216.66 -> 44.18Improved
re-train base detector on pseudo-labeled data from the PRCFaster R-CNN base detector · CUHK-Square (5% labeled)log-average miss rate: 0.3467 -> 0.1924Improved
re-train base detector on pseudo-labeled data from the PRCFaster R-CNN base detector · MIT-Traffic (5% labeled)log-average miss rate: 0.3458 -> 0.1509Improved
re-train base detector on pseudo-labeled data from the PRCFaster R-CNN base detector · Caltech1X (5% labeled)log-average miss rate: 0.4565 -> 0.2379Improved
add synthesized instances when training the PRC (ablation)PRC · Caltech1X (5% labeled)log-average miss rateImproved
add mean feature matching term (ablation)PRC · Caltech1X (5% labeled)log-average miss rateImproved
compare PRC against fully supervised base detectorPRC trained with synthesized instances · CUHK-Square (5% labeled)log-average miss rateImproved
re-training the detector instead of using the PRC aloneBase detector re-trained vs PRC · Caltech1X (5% labeled)log-average miss rateImproved

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