AI Paper Atlas

Research map / Detection and segmentation / CNN features

Should All Proposals Be Treated Equally in Object Detection?

Yunsheng Li, Yinpeng Chen, Xiyang Dai, Dongdong Chen, Mengchen Liu, Pei Yu, Ying Jin, Lu Yuan, Zicheng Liu, Nuno Vasconcelos

ECCV 2022 · Detection and segmentation › CNN features · approach: Region-based and query-based detectors · 4 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 complexity loss L_c to the IoU loss (ablation)DPP · COCO val2017 (ResNet-50)AP: 41.1 -> 42.2Improved
add IoU loss L_iou to the complexity loss (ablation)DPP · COCO val2017 (ResNet-50)AP: 41.8 -> 42.2Improved
increase lambda from 10 to 100 (ablation)DPP · COCO val2017 (ResNet-50)AP: 42.2 -> 41.7Hurt
increase lambda from 10 to 300 (ablation)DPP · COCO val2017 (ResNet-50)AP: 42.2 -> 41.0Hurt
use lambda=1 instead of 10 (ablation)DPP · COCO val2017 (ResNet-50)AP: 42.1 vs 42.2No clear effect
add medium operator g1 to g0 (ablation)DPP last stage · COCO val2017 (ResNet-50)AP: 41.0 -> 41.7Improved
add identity operator g2 proposals to g0+g1 (ablation)DPP last stage · COCO val2017 (ResNet-50)AP: 41.7 -> 42.2Improved
replace Sparse R-CNN head by DPP-XLSparse R-CNN · COCO val2017 (ResNet-50)AP / GFLOPS: AP 45.0 -> 45.0, GFLOPS 25 -> 15Improved
use DPP-S instead of Sparse R-CNNSparse R-CNN · COCO val2017 (ResNet-50)AP: 45.0 -> 40.4 (decrease of 4.6 points, 12.5x less computation)Hurt
replace Sparse R-CNN with DPP-XL on MobileNetV2Sparse R-CNN · COCO val2017 (MobileNetV2)AP: 36.6 -> 36.9Improved
use DPP-S instead of Sparse R-CNN on MobileNetV2Sparse R-CNN · COCO val2017 (MobileNetV2)AP: 36.6 -> 35.7Hurt
add more stages of the detection headDPP · COCO val2017 (ResNet-50)AP: 15.6, 32.1, 39.3, 41.7, 42.0, 42.2Mixed

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