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

07/19/2020
by   Rohun Tripathi, et al.
0

The widely adopted sequential variant of Non Maximum Suppression (or Greedy-NMS) is a crucial module for object-detection pipelines. Unfortunately, for the region proposal stage of two/multi-stage detectors, NMS is turning out to be a latency bottleneck due to its sequential nature. In this article, we carefully profile Greedy-NMS iterations to find that a major chunk of computation is wasted in comparing proposals that are already far-away and have a small chance of suppressing each other. We address this issue by comparing only those proposals that are generated from nearby anchors. The translation-invariant property of the anchor lattice affords generation of a lookup table, which provides an efficient access to nearby proposals, during NMS. This leads to an Accelerated NMS algorithm which leverages Spatially Aware Priors, or ASAP-NMS, and improves the latency of the NMS step from 13.6ms to 1.2 ms on a CPU without sacrificing the accuracy of a state-of-the-art two-stage detector on COCO and VOC datasets. Importantly, ASAP-NMS is agnostic to image resolution and can be used as a simple drop-in module during inference. Using ASAP-NMS at run-time only, we obtain an mAP of 44.2%@25Hz on the COCO dataset with a V100 GPU.

READ FULL TEXT
research
03/12/2021

Probabilistic two-stage detection

We develop a probabilistic interpretation of two-stage object detection....
research
10/31/2022

Tech Report: One-stage Lightweight Object Detectors

This work is for designing one-stage lightweight detectors which perform...
research
07/25/2018

Toward Scale-Invariance and Position-Sensitive Region Proposal Networks

Accurately localising object proposals is an important precondition for ...
research
01/10/2019

Region Proposal by Guided Anchoring

Region anchors are the cornerstone of modern object detection techniques...
research
08/05/2019

Revisiting Feature Alignment for One-stage Object Detection

Recently, one-stage object detectors gain much attention due to their si...
research
05/27/2021

PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery

Non-maximum Suppression (NMS) is an essential postprocessing step in mod...
research
10/26/2018

A Scalable Pipelined Dataflow Accelerator for Object Region Proposals on FPGA Platform

Region proposal is critical for object detection while it usually poses ...

Please sign up or login with your details

Forgot password? Click here to reset