AI Paper Atlas

Research map / Detection and segmentation / CNN features

PackDet: Packed Long-Head Object Detector

Kun Ding, Guojin He, Huxiang Gu, Zisha Zhong, Shiming Xiang, Chunhong Pan

ECCV 2020 · Detection and segmentation › CNN features · approach: Box regression and loss design · 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 CH-GN cross-head group normalization (no PackOp) (ablation)PackDet head, Me=0 · COCO minivalAP: 38.9 -> 39.5Improved
add CH-GN cross-head group normalization (no PackOp) (ablation)PackDet head, Me=3 · COCO minivalAP: 39.4 -> 39.7Improved
apply packing at test time only (ablation)multi-branch head, Me=0 · COCO minivalAP: 38.9 -> 22.9Hurt
train and test with PackOp plus CH-GN (ablation)PackDet, Me=0 · COCO minivalinference time (ms): 67.4 -> 64.4Improved
train and test with PackOp plus CH-GN (ablation)PackDet, Me=3 · COCO minivalinference time (ms): 75.0 -> 65.3Improved
train and test with PackOp plus CH-GN (ablation)PackDet, Me=3 · COCO minivalAP: 39.4 -> 40.1Improved
pack three extra feature maps (Me=3 instead of 0) (ablation)PackDet · COCO minivalAP: 39.7 -> 40.1Improved
pack P3-P7 with an alternative pattern instead of the default (ablation)PackDet head · COCO minivalAP: 39.7 -> 39.3Hurt
use stair pattern instead of grid pattern for P6 packing (ablation)PackDet head · COCO minival, P6AP: 4.1 -> 12.6Improved
use stair pattern instead of side-by-side for P6 packing (ablation)PackDet head · COCO minival, P6AP: 9.3 -> 12.6Improved
pack P5-P7 with PackOp (ablation)PackDet head · COCO minival, P5-P7AP: 24.4 -> 24.7Improved
pack same-scale P5 features with grid pattern (ablation)PackDet head · COCO minival, P5AP: 14.7 -> 14.1Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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