AI Paper Atlas

Research map / Detection and segmentation / CNN features

HumanLiker: A Human-like Object Detector to Model the Manual Labeling Process

Haoran Wei, Ping Guo, Yangguang Zhu, Chenglong Liu, Peng Wang

NeurIPS 2022 · Detection and segmentation › CNN features · approach: Pedestrian and crowd detection · 0 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 first-stage top-left offset adjustment (ablation)HumanLiker · COCO val2017, Swin-TAP: 46.7 -> 47.1Improved
Add stage-two fine trimming (regression) branch (ablation)HumanLiker · COCO val2017, Swin-TAP: 45.4 -> 47.1Improved
Use multiple cascade blocks instead of one (ablation)HumanLiker · COCO val2017, Swin-TAP: 46.2 -> 47.1Improved
Use multiple cascade blocks instead of one (ablation)HumanLiker · COCO val2017, Swin-TFPS: 20 -> 18Hurt
Add corner pooling (CP) (ablation)HumanLiker · COCO val2017, Swin-TAP: 47.1 -> 47.1No clear effect
Add corner pooling (CP) (ablation)HumanLiker · COCO val2017, Swin-TFPS: 18 -> 15Hurt
Add criss-cross attention (CCA) (ablation)HumanLiker · COCO val2017, Swin-TAP: 47.1 -> 47.0No clear effect
Add criss-cross attention (CCA) (ablation)HumanLiker · COCO val2017, Swin-TFPS: 18 -> 16Hurt
Estimate top-left corner instead of center as keypoint (ablation)keypoint model · MS-COCO training losstraining lossImproved
Replace center-guided Deformable DETR with HumanLiker (ResNeXt-101-DCN)HumanLiker · COCO test-devAP: 50.1 -> 50.2Improved
Replace Deformable DETR with HumanLikerHumanLiker · COCO test-devAP50: 69.7 -> 67.9Hurt
Replace Cascade R-CNN with HumanLikerHumanLiker · COCO test-devAP75: 52.9 -> 54.8Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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