PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery

05/27/2021
by   Tianyi Zhang, et al.
0

Non-maximum Suppression (NMS) is an essential postprocessing step in modern convolutional neural networks for object detection. Unlike convolutions which are inherently parallel, the de-facto standard for NMS, namely GreedyNMS, cannot be easily parallelized and thus could be the performance bottleneck in convolutional object detection pipelines. MaxpoolNMS is introduced as a parallelizable alternative to GreedyNMS, which in turn enables faster speed than GreedyNMS at comparable accuracy. However, MaxpoolNMS is only capable of replacing the GreedyNMS at the first stage of two-stage detectors like Faster-RCNN. There is a significant drop in accuracy when applying MaxpoolNMS at the final detection stage, due to the fact that MaxpoolNMS fails to approximate GreedyNMS precisely in terms of bounding box selection. In this paper, we propose a general, parallelizable and configurable approach PSRR-MaxpoolNMS, to completely replace GreedyNMS at all stages in all detectors. By introducing a simple Relationship Recovery module and a Pyramid Shifted MaxpoolNMS module, our PSRR-MaxpoolNMS is able to approximate GreedyNMS more precisely than MaxpoolNMS. Comprehensive experiments show that our approach outperforms MaxpoolNMS by a large margin, and it is proven faster than GreedyNMS with comparable accuracy. For the first time, PSRR-MaxpoolNMS provides a fully parallelizable solution for customized hardware design, which can be reused for accelerating NMS everywhere.

READ FULL TEXT
research
03/23/2018

Optimizing the Trade-off between Single-Stage and Two-Stage Object Detectors using Image Difficulty Prediction

There are mainly two types of state-of-the-art object detectors. On one ...
research
07/03/2018

Faster Bounding Box Annotation for Object Detection in Indoor Scenes

This paper proposes an approach for rapid bounding box annotation for ob...
research
05/22/2020

Hashing-based Non-Maximum Suppression for Crowded Object Detection

In this paper, we propose an algorithm, named hashing-based non-maximum ...
research
01/05/2022

Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection

Modern leading object detectors are either two-stage or one-stage networ...
research
04/17/2019

CenterNet: Object Detection with Keypoint Triplets

In object detection, keypoint-based approaches often suffer a large numb...
research
09/06/2021

Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection

We present a flexible and high-performance framework, named Pyramid R-CN...
research
07/19/2020

ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors

The widely adopted sequential variant of Non Maximum Suppression (or Gre...

Please sign up or login with your details

Forgot password? Click here to reset