AI Paper Atlas

Research map / Detection and segmentation / CNN features

MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection

Xin Lu, Quanquan Li, Buyu Li, Junjie Yan

ECCV 2020 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 89 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 T-head without mimic loss (ablation)MimicDet · COCO minival (ResNet-50, 1x)AP: 36.0 -> 36.4No clear effect
add head mimicking loss on top of T-head (ablation)MimicDet · COCO minival (ResNet-50, 1x)AP: 36.4 -> 39.0Improved
replace normal conv alignment layer with guided deformable conv in S-head (ablation)MimicDet · COCO minival (ResNet-50, 1x)AP: 33.7 -> 39.2Improved
replace plain deformable conv with guided deformable conv in S-head (ablation)MimicDet · COCO minival (ResNet-50, 1x)AP: 35.2 -> 39.2Improved
use heavy T-head instead of light T-head without dual-path mimicking (ablation)MimicDet · COCO minival (S-head AP, ResNet-50)AP: 37.5 -> 37.1Hurt
add dual-path (classification and regression) mimicking to heavy T-head (ablation)MimicDet · COCO minival (S-head AP, ResNet-50)AP: 37.1 -> 39.0Improved
use staggered feature pyramid (T-head on P2-P6, S-head on P3-P7) (ablation)MimicDet · COCO minival (ResNet-50, 1x)AP: 38.4 -> 39.0Improved
use shared backbone instead of separated pre-trained teacher backbone (ResNet-50) (ablation)MimicDet · COCO minival (2x schedule)AP: 40.2 -> 39.8; training time 34h -> 17.5hMixed
use shared backbone instead of separated pre-trained teacher backbone (ResNet-101) (ablation)MimicDet · COCO minival (2x schedule)AP: 42.2 -> 41.8; training time 47h -> 22hMixed
increase input size from 400 to 800 (ResNet-50)MimicDet · COCO minival (2x schedule)AP: 35.5 -> 39.8Improved
increase input size from 400 to 800 (ResNet-101)MimicDet · COCO minival (2x schedule)AP: 36.1 -> 41.8Improved

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