AI Paper Atlas

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

Pixel-Wise Crowd Understanding via Synthetic Data

Qi Wang, Junyu Gao, Wenbin Lin, Yuan Yuan

IJCV 2020 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 135 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 segmentation as a multi-task objective (MTL vs single task) (ablation)SFCN · GCC, random splitMAE: 36.2 -> 33.9Improved
add segmentation as a multi-task objective (MTL vs single task) (ablation)SFCN · GCC, cross-camera splitMAE: 56.0 -> 52.6Improved
add segmentation as a multi-task objective (MTL vs single task) (ablation)SFCN · GCC, cross-location splitMAE: 89.3 -> 85.7Improved
pre-train on GCC instead of ImageNet then fine-tune (ablation)SFCN† · UCF-QNRFMAE: 114.8 -> 102.0Improved
pre-train on GCC plus real datasets (Pre-GU) instead of ImageNet (ablation)SFCN† · UCF-QNRFMAE: 114.8 -> 98.6Improved
pre-train on GCC instead of training from scratch (ablation)MCNN · UCF-QNRFMAE: 281.2 -> 199.8Improved
pre-train on GCC instead of ImageNet, evaluate cross-dataset on SHT A (ablation)SFCN† · SHT AMAE: 108.0 -> 101.4Improved
pre-train on GCC instead of ImageNet, evaluate cross-dataset on SHT B (ablation)SFCN† · SHT BMAE: 17.2 -> 14.2Improved
use more GCC pre-training data (20% to 100%) (ablation)SFCN · UCF-QNRF and SHT BMAE and MSEImproved
pre-train on high-luminance GCC data instead of low-luminance (ablation)SFCN · UCF-QNRFMAE: 126.7 -> 117.2Improved
pre-train on denser scene levels L5-L6 instead of L0-L2 (ablation)SFCN · UCF-QNRFMAE: 131.4 -> 117.0Improved
use ResNet-101 backbone (SFCN dagger) instead of VGG-16 SFCN (ablation)SFCN · GCC, random splitMAE: 36.2 -> 28.1Improved

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