AI Paper Atlas

Research map / Detection and segmentation / CNN features

ObjectBox: From Centers to Boxes for Anchor-Free Object Detection

Mohsen Zand, Ali Etemad, Michael Greenspan

ECCV 2022 · Detection and segmentation › CNN features · approach: Box regression and loss design · 92 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
augment the center cell with neighboring cells for regression (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 33.1 -> 46.8Improved
add h-centers to the augmented center locations (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 46.8 -> 41.7Hurt
regress from 4 box corners instead of center (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 46.8 -> 28.2Hurt
add the center location to 4 corners (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 28.2 -> 37.4Improved
predict 4 boxes per location instead of 1 (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 46.8 -> 37.3Hurt
impose scale constraints m={0,64,128,inf} on feature levels (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 46.8 -> 35.8Hurt
impose scale constraints m={0,256,512,inf} on feature levels (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 46.8 -> 27.3Hurt
replace MSE loss with SDIoU loss (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 22.6 -> 46.8Improved
replace GIoU loss with SDIoU loss (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 27.4 -> 46.8Improved
replace CIoU loss with SDIoU loss (ablation)ObjectBox (CSPDarknet) · MS-COCOAP: 27.1 -> 46.8Improved
use CSPDarknet backbone instead of ResNet-101ObjectBox · MS-COCOAP: 46.1 -> 46.8Improved
treat all objects as positives at all scales (ObjectBox) versus FCOSObjectBox vs FCOS · MS-COCOAP: +4 %Improved

Later papers that compared with this method

1 later accepted paper reports ObjectBox as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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