Object Detection Made Simpler by Eliminating Heuristic NMS

by   Qiang Zhou, et al.

We show a simple NMS-free, end-to-end object detection framework, of which the network is a minimal modification to a one-stage object detector such as the FCOS detection model [Tian et al. 2019]. We attain on par or even improved detection accuracy compared with the original one-stage detector. It performs detection at almost the same inference speed, while being even simpler in that now the post-processing NMS (non-maximum suppression) is eliminated during inference. If the network is capable of identifying only one positive sample for prediction for each ground-truth object instance in an image, then NMS would become unnecessary. This is made possible by attaching a compact PSS head for automatic selection of the single positive sample for each instance (see Fig. 1). As the learning objective involves both one-to-many and one-to-one label assignments, there is a conflict in the labels of some training examples, making the learning challenging. We show that by employing a stop-gradient operation, we can successfully tackle this issue and train the detector. On the COCO dataset, our simple design achieves superior performance compared to both the FCOS baseline detector with NMS post-processing and the recent end-to-end NMS-free detectors. Our extensive ablation studies justify the rationale of the design choices.


page 7

page 10


OneNet: Towards End-to-End One-Stage Object Detection

End-to-end one-stage object detection trailed thus far. This paper disco...

FCOS: A simple and strong anchor-free object detector

In computer vision, object detection is one of most important tasks, whi...

BirdNet+: End-to-End 3D Object Detection in LiDAR Bird's Eye View

On-board 3D object detection in autonomous vehicles often relies on geom...

Instance Shadow Detection with A Single-Stage Detector

This paper formulates a new problem, instance shadow detection, which ai...

Learning non-maximum suppression

Object detectors have hugely profited from moving towards an end-to-end ...

LabelEnc: A New Intermediate Supervision Method for Object Detection

In this paper we propose a new intermediate supervision method, named La...

Object sieving and morphological closing to reduce false detections in wide-area aerial imagery

For object detection in wide-area aerial imagery, post-processing is usu...