Hashing-based Non-Maximum Suppression for Crowded Object Detection

• URL: http://arxiv.org/abs/2005.11426v1
• Date: Fri, 22 May 2020 23:45:59 GMT
• Title: Hashing-based Non-Maximum Suppression for Crowded Object Detection
• Authors: Jianfeng Wang, Xi Yin, Lijuan Wang, Lei Zhang
• Abstract summary: 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.
• Score: 63.761451382081844
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose an algorithm, named hashing-based non-maximum suppression (HNMS) to efficiently suppress the non-maximum boxes for object detection. Non-maximum suppression (NMS) is an essential component to suppress the boxes at closely located locations with similar shapes. The time cost tends to be huge when the number of boxes becomes large, especially for crowded scenes. The basic idea of HNMS is to firstly map each box to a discrete code (hash cell) and then remove the boxes with lower confidences if they are in the same cell. Considering the intersection-over-union (IoU) as the metric, we propose a simple yet effective hashing algorithm, named IoUHash, which guarantees that the boxes within the same cell are close enough by a lower IoU bound. For two-stage detectors, we replace NMS in region proposal network with HNMS, and observe significant speed-up with comparable accuracy. For one-stage detectors, HNMS is used as a pre-filter to speed up the suppression with a large margin. Extensive experiments are conducted on CARPK, SKU-110K, CrowdHuman datasets to demonstrate the efficiency and effectiveness of HNMS. Code is released at \url{https://github.com/microsoft/hnms.git}.

Related papers

• Sparse-Inductive Generative Adversarial Hashing for Nearest Neighbor Search [8.020530603813416]
  We propose a novel unsupervised hashing method, termed Sparsity-Induced Generative Adversarial Hashing (SiGAH) SiGAH encodes large-scale high-scale high-dimensional features into binary codes, which solves the two problems through a generative adversarial training framework. Experimental results on four benchmarks, i.e. Tiny100K, GIST1M, Deep1M, and MNIST, have shown that the proposed SiGAH has superior performance over state-of-the-art approaches.
  arXiv  Detail & Related papers  (2023-06-12T08:07:23Z)
• Asymmetric Scalable Cross-modal Hashing [51.309905690367835]
  Cross-modal hashing is a successful method to solve large-scale multimedia retrieval issue. We propose a novel Asymmetric Scalable Cross-Modal Hashing (ASCMH) to address these issues. Our ASCMH outperforms the state-of-the-art cross-modal hashing methods in terms of accuracy and efficiency.
  arXiv  Detail & Related papers  (2022-07-26T04:38:47Z)
• Dense Teacher: Dense Pseudo-Labels for Semi-supervised Object Detection [83.8770773275045]
  We propose replacing the sparse pseudo-boxes with the dense prediction as a united and straightforward form of pseudo-label. Compared to the pseudo-boxes, our Dense Pseudo-Label (DPL) does not involve any post-processing method, thus retaining richer information. We name our proposed SS-OD algorithm that leverages the DPL as Dense Teacher.
  arXiv  Detail & Related papers  (2022-07-06T09:41:17Z)
• Dynamic Ensemble Selection Using Fuzzy Hyperboxes [10.269997499911668]
  This paper presents a new dynamic ensemble selection (DES) framework based on fuzzy hyperboxes called FH-DES. Each hyperbox can represent a group of samples using only two data points (Min and Max corners) For the first time, misclassified samples are used to estimate the competence of the classifiers, which has not been observed in previous fusion approaches.
  arXiv  Detail & Related papers  (2022-05-20T21:06:46Z)
• Confidence Propagation Cluster: Unleash Full Potential of Object Detectors [8.996530151621661]
  Most object detection methods obtain objects by using the non-maximum suppression (NMS) and its improved versions like Soft-NMS to remove redundant bounding boxes. We challenge those NMS-based methods from three aspects: 1) The bounding box with highest confidence value may not be the true positive having the biggest overlap with the ground-truth box, 2) Not only suppression is required for redundant boxes, but also confidence enhancement is needed for those true positives, and 3) Sorting candidate boxes by confidence values is not necessary so that full parallelism is achievable. In this paper, inspired by belief propagation (BP), we propose the
  arXiv  Detail & Related papers  (2021-12-01T08:22:00Z)
• Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections [50.096540945099704]
  We propose a novel ensemble called the Probabilistic Ranking Aware Ensemble (PRAE) that refines the confidence of bounding boxes from detectors. We also introduce a bandit approach to address the confidence imbalance problem caused by the need to deal with different numbers of boxes.
  arXiv  Detail & Related papers  (2021-05-07T09:37:06Z)
• SMYRF: Efficient Attention using Asymmetric Clustering [103.47647577048782]
  We propose a novel type of balanced clustering algorithm to approximate attention. SMYRF can be used as a drop-in replacement for dense attention layers without any retraining. We show that SMYRF can be used interchangeably with dense attention before and after training.
  arXiv  Detail & Related papers  (2020-10-11T18:49:17Z)
• ASAP-NMS: Accelerating Non-Maximum Suppression Using Spatially Aware Priors [26.835571059909007]
  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.
  arXiv  Detail & Related papers  (2020-07-19T21:15:48Z)
• 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)

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.