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

Autor:	Hao, Shuaizheng, Liu, Hongzhe, Wang, Ningwei, Xu, Cheng
Rok vydání:	2021
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: The paper is under consideration at Pattern Recognition Letters
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2112.08902 Zobrazit plný text záznamu View this record from Arxiv