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

• URL: http://arxiv.org/abs/2007.09785v2
• Date: Fri, 21 Aug 2020 15:18:57 GMT
• Title: ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors
• Authors: Rohun Tripathi, Vasu Singla, Mahyar Najibi, Bharat Singh, Abhishek Sharma and Larry Davis
• Abstract summary: Non Maximum Suppression (or Greedy-NMS) is a crucial module for object-detection pipelines. For the region proposal stage of two/multi-stage detectors, NMS is turning out to be a latency bottleneck due to its sequential nature. We use ASAP-NMS to improve 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.
• Score: 26.835571059909007
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Accelerating Non-Maximum Suppression: A Graph Theory Perspective [24.34791528442417]
  Non-maximum suppression (NMS) is an indispensable post-processing step in object detection. This paper systematically analyzes NMS from a graph theory perspective for the first time, revealing its intrinsic structure. We introduce NMS-Bench, the first benchmark designed to comprehensively assess various NMS methods.
  arXiv  Detail & Related papers  (2024-09-30T17:20:49Z)
• Fuzzy-NMS: Improving 3D Object Detection with Fuzzy Classification in NMS [19.452760776980472]
  Non-maximum suppression (NMS) is an essential post-processing module used in many 3D object detection frameworks. We introduce fuzzy learning into NMS and propose a novel generalized Fuzzy-NMS module to achieve finer candidate bounding box filtering.
  arXiv  Detail & Related papers  (2023-10-21T09:09:03Z)
• ANMS: Asynchronous Non-Maximum Suppression in Event Stream [15.355579943905585]
  Non-maximum suppression (NMS) is widely used in frame-based tasks as an essential post-processing algorithm. This paper proposes a general-purpose asynchronous non-maximum suppression pipeline (ANMS) The proposed pipeline extract fine feature stream from the output of original detectors and adapts to the speed of motion.
  arXiv  Detail & Related papers  (2023-03-19T05:33:32Z)
• ISDA: Position-Aware Instance Segmentation with Deformable Attention [4.188555841288538]
  We propose a novel end-to-end instance segmentation method termed ISDA. It reshapes the task into predicting a set of object masks, which are generated via traditional convolution operation. Thanks to the introduced set-prediction mechanism, the proposed method is NMS-free.
  arXiv  Detail & Related papers  (2022-02-23T12:30:18Z)
• PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery [17.704037442897004]
  Non-maximum Suppression (NMS) is an essential postprocessing step in modern convolutional neural networks for object detection. The de-facto standard for NMS, namely GreedyNMS, cannot be easily parallelized. MaxpoolNMS is introduced as a parallelizable alternative to GreedyNMS.
  arXiv  Detail & Related papers  (2021-05-27T08:24:21Z)
• VL-NMS: Breaking Proposal Bottlenecks in Two-Stage Visual-Language Matching [75.71523183166799]
  The prevailing framework for matching multimodal inputs is based on a two-stage process. We argue that these methods overlook an obvious emphmismatch between the roles of proposals in the two stages. We propose VL-NMS, which is the first method to yield query-aware proposals at the first stage.
  arXiv  Detail & Related papers  (2021-05-12T13:05:25Z)
• Object Detection Made Simpler by Eliminating Heuristic NMS [70.93004137521946]
  We show a simple NMS-free, end-to-end object detection framework. We attain on par or even improved detection accuracy compared with the original one-stage detector.
  arXiv  Detail & Related papers  (2021-01-28T02:38:29Z)
• End-to-End Object Detection with Fully Convolutional Network [71.56728221604158]
  We introduce a Prediction-aware One-To-One (POTO) label assignment for classification to enable end-to-end detection. A simple 3D Max Filtering (3DMF) is proposed to utilize the multi-scale features and improve the discriminability of convolutions in the local region. Our end-to-end framework achieves competitive performance against many state-of-the-art detectors with NMS on COCO and CrowdHuman datasets.
  arXiv  Detail & Related papers  (2020-12-07T09:14:55Z)
• Ref-NMS: Breaking Proposal Bottlenecks in Two-Stage Referring Expression Grounding [80.46288064284084]
  Ref-NMS is the first method to yield expression-aware proposals at the first stage. Ref-NMS regards all nouns in the expression as critical objects, and introduces a lightweight module to predict a score for aligning each box with a critical object. Since Ref- NMS is agnostic to the grounding step, it can be easily integrated into any state-of-the-art two-stage method.
  arXiv  Detail & Related papers  (2020-09-03T05:04:12Z)
• FCOS: A simple and strong anchor-free object detector [111.87691210818194]
  We propose a fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion. Almost all state-of-the-art object detectors such as RetinaNet, SSD, YOLOv3, and Faster R-CNN rely on pre-defined anchor boxes. In contrast, our proposed detector FCOS is anchor box free, as well as proposal free.
  arXiv  Detail & Related papers  (2020-06-14T01:03:39Z)
• Hashing-based Non-Maximum Suppression for Crowded Object Detection [63.761451382081844]
  We propose an algorithm, named hashing-based non-maximum suppression (HNMS) to efficiently suppress the non-maximum boxes for object detection. For two-stage detectors, we replace NMS in region proposal network with HNMS, and observe significant speed-up with comparable accuracy. Experiments are conducted on CARPK, SKU-110K, CrowdHuman datasets to demonstrate the efficiency and effectiveness of HNMS.
  arXiv  Detail & Related papers  (2020-05-22T23:45:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.