AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Self-Supervised Human Detection and Segmentation via Background Inpainting

Isinsu Katircioglu, Helge Rhodin, Victor Constantin, Jörg Spörri, Mathieu Salzmann, Pascal Fua

TPAMI 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 22 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 the L_v mask prior (vs none) (ablation)Ours w/o optical flow · Ski PTZ dataset (validation)J measure: 0.51 -> 0.67Improved
use L_v prior instead of L1 prior (ablation)Ours w/o optical flow · Ski PTZ dataset (validation)J measure: 0.62 -> 0.67Improved
use L_v prior instead of L2 prior (ablation)Ours w/o optical flow · Ski PTZ dataset (validation)J measure: 0.61 -> 0.67Improved
add ImageNet pre-training (vs random init) (ablation)Ours w/o optical flow · Ski PTZ dataset (validation)J measure: 0.60 -> 0.67Improved
ImageNet weights vs unsupervised pre-training (ablation)Ours w/o optical flow · Ski PTZ dataset (validation)J measure: 0.62 -> 0.67No clear effect
add optical flow supervision during training (ablation)Ours · Ski PTZ dataset (test)J measure: 0.62 -> 0.70Improved
add optical flow supervision during training (ablation)Ours · Handheld dataset (test)J measure: 0.75 -> 0.70Hurt
add optical flow supervision during training (ablation)Ours · Iceskating dataset (test)J measure: 0.66 -> 0.69Improved
add CRF post-processing (ablation)Ours w/ optical flow · Ski PTZ dataset (test)F measure: 0.77 -> 0.83Improved
add CRF post-processing (ablation)Ours w/ optical flow · Handheld dataset (test)J measure: 0.70 -> 0.76Improved
use Monte Carlo importance sampling instead of Gumbel-Softmax (ablation)Ours · Human3.6M (detection)mAP@0.5: 0.30 -> 0.58Improved
use importance sampling instead of uniform sampling (ablation)Ours · Human3.6M (detection)convergenceImproved

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