NCMS: Towards accurate anchor free object detection through ℓ2 norm calibration and multi-feature selection

Abstract We present simple and flexible drop-in modules in feature pyramids for general object detection, which can be easily generalized to other anchor-free detectors without introducing extra parameters, and only involves negligible computational cost on training and testing. The proposed detector, called NCMS, inserts a simple norm calibration (NC) operation between the feature pyramids and detection head to alleviate and balance the norm bias caused by feature pyramid network (FPN). Furthermore, the NCMS leverages an enhanced multi-feature selective strategy (MS) during training to assign the ground-truth to particular feature pyramid levels as supervisions, in order to obtain more discriminative representation for objects. By generalizing to the state-of-the-art FSAF module (Zhu et al., 2019), our NCMS improves it by 1.6% on COCO val set without bells and whistles. The resulting best model achieves 44.0% mAP with single-model and single-scale testing, which is a fairly competitive result.