Papers › Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection

Toward Minimal Misalignment at Minimal Cost in One-Stage and Anchor-Free Object Detection

16 Dec 2021arXiv:2112.08902archive 2025-07-28

Shuaizheng Hao, Hongzhe Liu, Ningwei Wang, Cheng Xu

Common object detection models consist of classification and regression branches, due to different task drivers, these two branches have different sensibility to the features from the same scale level and the same spatial location. The point-based prediction method, which is based on the assumption that the high classification confidence point has the high regression quality, leads to the misalignment problem. Our analysis shows, the problem is further composed of scale misalignment and spatial misalignment specifically. We aim to resolve the phenomenon at minimal cost: a minor adjustment of the head network and a new label assignment method replacing the rigid one. Our experiments show that, compared to the baseline FCOS, a one-stage and anchor-free object detection model, our model consistently get around 3 AP improvement with different backbones, demonstrating both simplicity and efficiency of our method.

PaperPDFCode

Code

HaoGood/MOD officialpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Object Detectionobject-detectionregression

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionConvolutionFCOSFPNNon Maximum Suppression

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections